ICINCO 2019 Abstracts

Area 1 - Industrial Informatics

Full Papers

Paper Nr:	108
Title:	An IoT Framework for Assembly Tracking and Scheduling in Manufacturing SME
Authors:	Meysam Minoufekr, Anass Driate and Peter Plapper
Abstract:	A universal RFID platform is presented, which is meant to be used as a building component of IoT integrated collaboration platform for manufacturing applications. The core element of the system is based on affordable Raspberry Pi modules, running on an IoT operating system. The main goal of this paper is to demonstrate an affordable IoT solution for manufacturing SME to improve productivity by measuring and adapting the assembly processes for a given product. To track the production chain, each part in the supply chain is equipped with an RFID tag, which will be recorded during its travel through the facility. In addition, each worker has his own RFID tag to localize himself and record the performed activities. The workstations are equipped with RFID scanners used to record activity and product flow through the stations. All the gathered data is collected on a server and the real-time status of the assembly line is processed and displayed to the dispatching agents. Upon this data analysis, the dispatchers can take actions, update the manufacturing setup and ultimately increase productivity.
Download

Paper Nr:	190
Title:	Modular and Domain-guided Multi-robot Planning for Assembly Processes
Authors:	Ludwig Nägele, Andreas Schierl, Alwin Hoffmann and Wolfgang Reif
Abstract:	Smart factories of the future will be equipped with dynamic and task-specific teams of robots in order to manufacture custom-tailored products. For this, it is necessary to facilitate the planning of appropriate task sequences for cooperating robots. In this paper, we introduce a modular and domain-guided planning approach for multiple robots. Due to its modularity, the approach can be adapted to different assembly problems. Moreover, domain knowledge is used to guide the planning towards feasible solutions. We evaluate the approach with different examples from the blocks world domain (i. e. LEGO® DUPLO® ). This evaluation shows that this domain-guided approach outperforms classical planning based on state space search such as A*.
Download

Short Papers

Paper Nr:	64
Title:	An Innovative Automated Robotic System based on Deep Learning Approach for Recycling Objects
Authors:	Jaeseok Kim, Olivia Nocentini, Marco Scafuro, Raffaele Limosani, Alessandro Manzi, Paolo Dario and Filippo Cavallo
Abstract:	In this paper, an industrial robotic recycling system that is able to grasp objects and sort them according to their materials is presented. The system architecture is composed of a robot manipulator with a multifunctional grasping tool, one platform, a depth and an RGB camera. The innovation of this work consists of integrating image processing, grasping, motion planning and object material classification to create a new automated recycling system framework. An efficient object recognition approach is presented that uses segmentation and finds grasping points to properly manipulate objects. A deep learning approach was also used with a modified LeNet model for waste objects classification, sorting them into two main classes: carton and plastic. Image processing and classification were integrated with motion planning that is used to move the robot with optimized trajectories. To evaluate the system, the success rate and the execution time for grasping and object classification were computed. In addition, the accuracy of the network model was evaluated. A total success rate of 86.09% and 90% was obtained for carton and plastic samples grasped using suction, while 86.67% and 78.57% using gripper. In addition, a classification accuracy of 96% was reached on test samples
Download

Paper Nr:	102
Title:	Modelling of CNC Machine Tools for Augmented Reality Assistance Applications using Microsoft Hololens
Authors:	Meysam Minoufekr, Pascal Schug, Pascal Zenker and Peter Plapper
Abstract:	With the ongoing development of both, augmented and virtual reality new important paths open for the use of computer aided manufacturing. Microsoft’s new mixed reality device, the HoloLens bridges the gap between reality and digital content by injecting holograms into the user’s field of view. This new way of showcasing digital data enable whole new fields to for development. In this paper, the verification of CNC machining with the Microsoft Hololens will be illustrated and examined. This paper will introduce a framework which enables users to perform machine simulation using Augmented Reality. Machine models can be picked on a remote computer and be loaded into the Hololens as holograms. Through the framework they can be simulated, and the machining processes observed before the actual process starts.
Download

Paper Nr:	148
Title:	Deep Neural Networks for New Product Form Design
Authors:	Chun-Chun Wei, Chung-Hsing Yeh, Ian Wang, Bernie Walsh and Yang-Cheng Lin
Abstract:	Neural Networks (NNs) are non-linear models and are widely used to model complex relationships, thus being well suited to formulate the product design process for matching design form elements to consumers’ affective preferences. In this paper, we construct 36 deep NN models, using one to four hidden layers with three different dropout ratios and three widely used rules for determining the number of neurons in the hidden layer(s). As a result of extensive experiments, the NN model using one hidden layer with 140 hidden neurons has the highest predicting accuracy rate (80%) and is used to help product designers determine the optimal form combination for new fragrance bottle design.
Download

Paper Nr:	37
Title:	The Effect of Baffles on Heat Transfer
Authors:	Raheleh Jafari, Sina Razvarz, Cristóbal Vargas-Jarillo and Alexander Gegov
Abstract:	For a long time technicians and engineers have used geometric changes of objects for the purpose of enhancement of heat transfer. The discovery and use of nanofluids and their unique properties lead to a new revolution on the heat transfer. This paper presents the simulation of Ansis software applied to the flow tube with a constant flux, also studies the effect of baffles and the use of nano particles on heat transfer.
Download

Paper Nr:	90
Title:	Interdisciplinary Approach to Cyber-physical Systems Training
Authors:	Radda A. Iureva, Artem S. Kremlev, Alexey A. Margun, Sergey M. Vlasov, Sergey D. Vasilkov, Alexandr V. Penskoi, Dmitry E. Konovalov and Pavel Y. Korepanov
Abstract:	In this paper, the authors examine the importance of a transdisciplinary approach to cyber-physical systems training. The article concludes that it is necessary to introduce new educational models that will contribute to the formation of innovative thinking of master students. The use of a multidisciplinary approach in the training of master students is substantiated, and a combined scheme of interdisciplinary and multidisciplinary methods is proposed on the example of the disciplines "Cyber-physical systems and technologies." Specialization lies in the fact that not only the available baggage knowledge, but also ways to find their knowledge in a new application, including in non-standard conditions, readiness for self-development and improvement information. The ability of the current educational model to meet the requirements has been established.
Download

Paper Nr:	111
Title:	Formalizing the Safety Functions to Assure the Software Quality of NPP Safety Important Systems
Authors:	Elena P. Jharko
Abstract:	One of the most critical tasks in the software complexes quality assurance is the procedure of forming requirements to a developed or modified system and subsequent their verification. The essential errors are making in the first life cycle stages – these are errors in determining requirements, selecting the architecture, high-level design. Faults of safety critically important software may considerably damage the equipment or properties, as well to lead to an essential detriment of the environment and human victims. Increasing requirements to the software quality of NPP (nuclear power plant) safety important systems at all stages of the life cycle is concerned with increasing the software complexity and functionality and has led the necessity of developing approaches to justify both the system itself safety and software involved in the systems makeup. In the paper, an approach is considered, based on the “safety functions”, meeting which in the sequel is verifying. This approach is used under the soft- and hardware complexes software assurance of upper level systems of automated process control systems and may be applied for the fault tolerance analysis, information- and cybersecurity of soft- and hardware complexes.
Download

Paper Nr:	147
Title:	I-AM: Interface for Additive Manufacturing
Authors:	Marco Rodrigues, João P. Pereira and Pedro M. Moreira
Abstract:	The shift of the computational paradigm to a model where there is a multiplicity of computational devices capable of feeling and acting on the environment allied to the digital transformation of manufacturing processes, with an increasing real-virtual fusion, are two of the pillars of the ongoing industrial revolution industry coined as Industry 4.0. In the context of new manufacturing environments, the development interfaces that are usable, intelligible, interactive and easy-to-implement and deploy across multiple device is a major aspiration to be achieved. This paper describes the design process of an interface, supported by web standards, adapted for additive manufacturing appliances. This interface aims to allow the monitoring of the production parameters, providing the operator with all the information related to the manufacturing process and the equipment and materials involved. Beyond providing an effective tool to monitor and control of the real manufacturing process, it also allows to virtually simulate the process, thus enabling optimization and anticipation of possible issues. The adopted user-centered design methodology is described, as well as the proposed architecture. Details are presented on the developed prototypes, the users studies, and about the information collected from users for the requirements elicitation process and from the tests. The interface was developed through several iterations and was evaluated very positively by the users (operators) using established usability assessment instruments and methods. In the near future it is intended to generalize the approach and architecture to move towards a framework dedicated to the design and implementation of universal interfaces for industrial environments.
Download

Paper Nr:	158
Title:	Inventory Routing Problem with Non-stationary Stochastic Demands
Authors:	Ehsan Yadollahi, El-Houssaine Aghezzaf, Joris Walraevens and Birger Raa
Abstract:	In this paper we solve Stochastic Periodic Inventory Routing Problem (SPIRP) when the accuracy of expected demand is changing among the periods. The variability of demands increases from period to period. This variability follows a certain rate of uncertainty. The uncertainty rate shows the change in accuracy level of demands during the planning horizon. To deal with the growing uncertainty, we apply a safety stock based SPIRP model with different levels of safety stock. To satisfy the service level in the whole planning horizon, the level of safety stock needs to be adjusted according to the demand’s variability. In addition, the behavior of the solution model in long term planning horizons for retailers with different demand accuracy is taken into account. We develop the SPIRP model for one retailer with an average level of demand, and standard deviation for each period. The objective is to find an optimum level of safety stock to be allocated to the retailer, in order to achieve the expected level of service, and minimize the costs. We propose a model to deal with the uncertainty in demands, and evaluate the performance of the model based on the defined indicators and experimentally designed cases.
Download

Paper Nr:	192
Title:	Software 2.0 for Scrap Metal Classification
Authors:	Manuel Robalinho and Pedro Fernandes
Abstract:	Software 2.0 and its approach to the processing of multi-spectral images helping to perform an automatic classification of metal scrap is the subject of this research. The use of Machine Learning and Deep Learning tools contribute to the development of intelligent systems, allowing to achieve relevant results in the classification of images, particularly of metal scrap. In this research, tests will be performed with a multi-spectral chamber to obtain images of aluminum, iron, copper, brass, stainless steel, simulating an environment of metal scrap. The aim is to obtain the classification of these metals through the development of software and to perform a multi-spectral analysis of the obtained images. Preliminary tests were made in a controlled environment, with a small sample of these materials. Studies to implement a prototype in a Brazilian steel industry will follow.
Download

Area 2 - Intelligent Control Systems and Optimization

Full Papers

Paper Nr:	12
Title:	Fault Training Matrix for Process Monitoring based on Structured Residuals
Authors:	Khaoula Tidriri, Nizar Chatti, Sylvain Verron and Teodor Tiplica
Abstract:	Fault Detection and Diagnosis (FDD) approaches have become increasingly important due to the growing demand for reliability and safety for modern systems. During the last decades, many works were reported about FDD approaches, especially model-based ones. The latter relies solely on a developed model that accurately describes the system, without exploiting any additional available data. In this work, we intent to make use of the physical model as well as historical data, for both normal operating state and faulty states. Hence, the paper focuses on the validation of an experimental approach, called Fault Training Analysis, that analyzes and identifies the causal relations between residuals and faults identified and observed on the system, by dealing with real measurement data from nominal and faulty states. It results on an experimental matrix, called Fault Training Matrix, that enhances the theoretical Fault Signature Matrix. The effectiveness of the proposed approach is validated through the challenging Tennessee Eastman Process. The application results on a high fault detection rate, a high fault diagnosis rate and a small false alarm rate.
Download

Paper Nr:	21
Title:	A PGD-based Method for Robot Global Path Planning: A Primer
Authors:	N. Montés, F. Chinesta, A. Falcó, M. C. Mora, L. Hilario and J. L. Duval
Abstract:	The present paper shows, for the first time, the technique known as PGD-Vademecum as a global path planner for mobile robots. The main idea of this method is to obtain a Vademecum containing all the possible paths from any start and goal positions derived from a harmonic potential field in a predefined map. The PGD is a numerical technique with three main advantages. The first one is the ability to bring together all the possible Poisson equation solutions for all start and goal combinations in a map, guaranteeing that the resulting potential field does not have deadlocks. The second one is that the PGD-Vademecum is expressed as a sum of uncoupled multiplied terms: the geometric map and the start and goal configurations. Therefore, the harmonic potential field for any start and goal positions can be reconstructed extremely fast, in a nearly negligible computational time, allowing real-time path planning. The third one is that only a few uncoupled parameters are required to reconstruct the potential field with a low discretization error. Simulation results are shown to validate the abilities of this technique.
Download

Paper Nr:	30
Title:	Generation of Complex Data for AI-based Predictive Maintenance Research with a Physical Factory Model
Authors:	Patrick Klein and Ralph Bergmann
Abstract:	Manufacturing systems naturally contain plenty of sensors which produce data primarily used by the control software to detect relevant status information of the actuators. In addition, sensors are included in order to monitor the health status of specific components, which enable to detect certain known, frequently occurring faults or undesired states of the system. While the identification of a failure by using the data of a sensor dedicated explicitly to its detection is a rather straightforward machine learning application, the detection of failures which only have an indirect effect on the data produced by a couple of other sensors is much more challenging. Therefore, a combination of different methods from Artificial Intelligence, in particular, machine learning and knowledge-based (semantic) approaches is required to identify relevant patterns (or failure modes). However, there are currently no appropriate research environments and data sets available that can be used for this kind of research. In this paper, we propose an approach for the generation of predictive maintenance data by using a physical Fischertechnik model factory equipped with several sensors. Different ways of reproducing real failures using this model are presented as well as a general procedure for data generation.
Download

Paper Nr:	59
Title:	Exploiting Physical Contacts for Robustness Improvement of a Dot-painting Mission by a Micro Air Vehicle
Authors:	Thomas Chaffre, Kevin Tudal, Sylvain Bertrand and Lionel Prevost
Abstract:	In this paper we address the problem of dot painting on a wall by a quadrotor Micro Air Vehicle (MAV), using on-board low cost sensors (monocular camera and IMU) for localization. A method is proposed to cope with uncertainties on the initial positioning of the MAV with respect to the wall and to deal with walls composed of multiple segments. This method is based on an online estimation algorithm that makes use of information of physical contacts detected by the drone during the flight to improve the positioning accuracy of the painted dots. Simulation results are presented to assess quantitatively the efficiency of the proposed approaches.
Download

Paper Nr:	76
Title:	Entry Trajectory Optimization via hp Pseudospectral Convex Programming
Authors:	Xiao Wang, Yulin Wang, Shengjing Tang and Jie Guo
Abstract:	In this paper, a hp pseudospectral sequential convex programming (hp-PSCP) method is proposed to solve the entry trajectory optimization problem. The hp flipped Radau pseudospectral method (FRPM) is utilized to discretize the nonlinear dynamics. By successive linearization technology and introducing new variables, the optimization problem is converted into a series of convex problems and solved by primal-dual interior-point method. Numerical results show that the proposed method provides a good compromise between computational accuracy and speed compared to existing convex methods.
Download

Paper Nr:	89
Title:	Safe Formation Control with Constrained Linear Model Predictive Control
Authors:	Philippe Feyel
Abstract:	This paper proposes a safe formation control technic based on the virtual leader-follower principle employed to build agents’ trajectory. Each agent tracks its own trajectory using exclusively constrained linear Model Predictive Control (MPC). To ensure non-collision during formation control and transient phases such as formation reconfigurations, and thanks to the flexibility of MPC, a simple and flexible method for establishing collision and obstacle avoidance linear constraints is proposed. The efficiency of the approach is illustrated by the safe formation control and reconfiguration of a swarm of quadrotor helicopters.
Download

Paper Nr:	107
Title:	Control Strategies for an Octopus-like Soft Manipulator
Authors:	Simone Cacace, Anna C. Lai and Paola Loreti
Abstract:	We investigate a reachability control problem for a soft manipulator inspired to an octopus arm. Cases modelling mechanical breakdowns of the actuators are treated in detail: we explicitly characterize the equilibria, and we provide numerical simulations of optimal control strategies.
Download

Paper Nr:	129
Title:	Optimal Active Target Localisation Strategy with Range-only Measurements
Authors:	Shaoming He, Hyo-Sang Shin and Antonios Tsourdos
Abstract:	This paper investigates the problem of one-step ahead optimal active sensing strategy to minimise estimation errors with range-only measurements for non-manoeuvring target. The determinant of Fisher Information Matrix (FIM) is utilized as the objective function in the proposed optimisation problem since it quantifies the volume of uncertainty ellipsoid of any efficient estimator. In consideration of physical velocity and turning rate constraints, the optimal heading angle command that maximises the cost function is derived analytically. Simulations are conducted to validate the analytical findings.
Download

Paper Nr:	152
Title:	An Improvement in a Local Observer Design for Optimal State Feedback Control: The Case Study of HIV/AIDS Diffusion
Authors:	Paolo Di Giamberardino and Daniela Iacoviello
Abstract:	The paper addresses the problem of an observer design for a nonlinear system for which a preliminary linear state feedback is designed but the full state is not measurable. Since a linear control assures the fulfilment of local approximated conditions, usually a linear observer is designed in these cases to estimate the state with estimation error locally convergent to zero. The case in which the control contains an external reference, like in regulations problems, is studied, showing that the solution obtained working with the linear approximation to get local solutions produces non consistent results in terms of local regions of convergence for the system and for the observer. A solution to this problem is provided, proposing a different choice for the observer design which allows to obtain all conditions locally satisfied on the same local region in the neighbourhood of a new equilibrium point. The case study of an epidemic spread control is used to show the effectiveness of the procedure. The linear control with regulation term is present in this case because the problem is reconducted to a Linear Quadratic Regulation problem. Simulation results show the differences between the two approaches and the effectiveness of the proposed one.
Download

Paper Nr:	155
Title:	Robust Calibration Procedure of a Manipulator and a 2D Laser Scanner using a 1D Calibration Target
Authors:	Jan Alberts, Sebastian P. Kleinschmidt and Bernardo Wagner
Abstract:	An accurate extrinsic calibration between a robots’ exteroceptive sensors and its manipulator is essential for tasks such as mobile manipulation and tactile exploration. Especially for extrinsic calibration of a manipulators’ end effector and 2D laser scanner, state-of-the-art approaches often require complex calibration targets or sensors which need to be mounted to the end effector. Therefore, such approaches are only suitable to a limited extent for use in mobile robotics. In this paper, we present a simple but effective approach to determine the six degrees of freedom transformation between the end effector of a serial manipulator and the center of a 2D laser scanner. In contrast to other approaches, our approach requires only a 1D target for calibration. Whereas complex calibration geometries often require a tool change for calibration, our approach is also applicable using practical objects like a drill mounted to the end effector. As a consequence, a tool change is not required for recalibration for many applications anymore. To evaluate the performance of our approach, we perform the calibration based on simulated as well as real data. We compare our results against the ground truth of a physically closed transformation chain using the lidars’ CAD data.
Download

Paper Nr:	191
Title:	Two Cases of Study for Control Reconfiguration of Discrete Event Systems (DES)
Authors:	I. Tahiri, A. Philippot, V. Carré-Ménétrier and A. Tajer
Abstract:	In this paper, we propose two cases of study for control reconfiguration of Discrete Event Systems. The main contributions are based on a safe centralized and distributed control synthesis founded on timed properties. In fact, if a sensor fault is detected, the controller of the normal behavior is reconfigured to a timed controller where the timed information replaces the information lost on the faulty sensor. Finally, we apply our contribution to a manufacturing system to illustrate our results and compare between the two frameworks.
Download

Paper Nr:	210
Title:	Visual Predictive Control of Robotic Arms with Overlapping Workspace
Authors:	E. L. Flécher, A. Durand-Petiteville, V. Cadenat and T. Sentenac
Abstract:	This paper deals with multi-arms fruits picking in orchards. More specifically, the goal is to control the arms to approach the fruits position. To achieve this task a VPC strategy has been designed to take into account the dynamic of the environment as well as the various constraints inherent to the mechanical system, visual servoing manipulation and shared workspace. Our solution has been evaluated in simulation using on PR2 arms model. Different models of visual features prediction have been tested and the entire VPC strategy has been run on various cases. The obtained results show the interest and the efficiency of this strategy to perform a fruit picking task.
Download

Paper Nr:	215
Title:	Clustering Algorithm for Generalized Recurrences using Complete Lyapunov Functions
Authors:	Carlos Argáez, Peter Giesl and Sigurdur Hafstein
Abstract:	Many advances and algorithms have been proposed to obtain complete Lyapunov functions for dynamical systems and to properly describe the chain-recurrent set, e.g. periodic orbits. Recently, a heuristic algorithm was proposed to classify and reduce the over-estimation of different periodic orbits in the chain-recurrent set, provided they are circular. This was done to investigate the effect on further iterations of the algorithm to compute approximations to a complete Lyapunov function. In this paper, we propose an algorithm that classifies the different connected components of the chain-recurrent set for general systems, not restricted to (circular) periodic orbits. The algorithm is based on identifying clustering of points and is independent of the particular algorithm to construct the complete Lyapunov functions.
Download

Paper Nr:	216
Title:	Lyapunov Functions for Linear Stochastic Differential Equations: BMI Formulation of the Conditions
Authors:	Sigurdur Hafstein
Abstract:	We present a bilinear matrix inequality (BMI) formulation of the conditions for a Lyapunov functions for autonomous, linear stochastic differential equations (SDEs). We review and collect useful results from the theory of stochastic stability of the null solution of an SDE. Further, we discuss the Itô- and Stratonovich interpretation and linearizations and Lyapunov functions for linear SDEs. Then we discuss the construction of Lyapunov functions for the damped pendulum, wihere the spring constant is modelled as a stochastic process. We implement in Matlab the characterization of its canonical Lyapunov function as BMI constraints and consider some practical implementation strategies. Further, we demonstrate that the general strategy is applicable to general autonomous and linear SDEs. Finally, we verify our findings by comparing with results from the literature.
Download

Paper Nr:	217
Title:	Algorithm and Software to Generate Code for Wendland Functions in Factorized Form
Authors:	Hjortur Bjornsson and Sigurdur Hafstein
Abstract:	In this paper we describe an algorithm to determine Wendland’s Radial Basis Functions in a specific factorized form. Additionally, we present a software tool that uses this algorithm to generate a C/C++ library that implements the Wendland functions with arbitrary parameters in factorized form. This library is more efficient and has higher numerical accuracy than previous implementations. The software tool is written in Python and is available for download.
Download

Short Papers

Paper Nr:	19
Title:	Mini-term 4.0. A Real-time Maintenance Support System to Prognosticate Breakdowns in Production Lines
Authors:	E. Garcia and N. Montes
Abstract:	This paper presents a Real-time Maintenance Support System (MSS) to prognosticate breakdowns in production lines. The system is based on the sub-cycle time monitoring, mini-terms, and how the sub-cycle time variability can be used as a deterioration indicator that could describe the dynamic of the failure for the machine parts. A Real-time MSS has been installed at Ford factory located in Almussafes (Valencia), the so-called Mini-term 4.0. At present, three plants, Body 1,2 and 3 have hundreds of mini-terms sensed by the system. The connected production line elements are the welding guns, elevators, screwdriver and scissor tables. Mini-term 4.0 uses the well-known k-means algorithm to detect change points. The K-means constructs two groups and, when centroid values differ more than 7 % (orange alert), or 18 % (red alert), an e-mail is sent to maintenance team to schedule the maintenance task. Some examples of the different change point topologies detected are shown at the end of the paper.
Download

Paper Nr:	22
Title:	A MEG Study of Different Motor Imagery Modes in Untrained Subjects for BCI Applications
Authors:	Alexander E. Hramov, Elena N. Pitsik, Parth Chholak, Vladimir A. Maksimenko, Nikita S. Frolov, Semen A. Kurkin and Alexander N. Pisarchik
Abstract:	Motor imagery is a most commonly studied neurophysiological pattern that is used in brain-computer interfaces as a command for exoskeletons, bioprostheses, wheelchair and other robotic devices. The mechanisms of motor imagery manifestation in human brain activity include dynamics of motor-related frequency bands in various brain areas, among which the most common is sensorimotor rhythnm. In present work we consider time-frequency structure of magnitoencephalographical (MEG) motor imagery in untrained subjects. We conduct series of experiments to collect MEG motor imagery dataset in untrained subjects. We confirm the emergence of two types of motor imagery – visual (VI) and kinesthetic (KI), which cause different types of event-related potentials (ERP) dynamics and require different approaches to classification using mashine learning methods. We also reveal the impact of dataset optimization on the artificial neural network performance, which is essential topic in brain-computer interface (BCI) development. We show that developing classification stratedy based on time-frequency features of the particular MEG signal can increase classification accuracy of the VI mode to the level of the KI.
Download

Paper Nr:	23
Title:	Automatic Temperature Measurement for Hot Spots in Face Region of Cattle using Infrared Thermography
Authors:	Mohammed A. Jaddoa, Adel A. Al-Jumaily, Luciano A. Gonzalez and Holly Cuthbertson
Abstract:	Infrared Thermography Technology (IRT) is a non-invasive method that has been used to calculate and display temperature as an Infrared thermal image. Infrared thermal images are used frequently to measure temperature remotely, and this temperature can be used as a health indicator for detecting diseases and inflammation in human and animal. In cattle, the rising temperature of the eye and nose region used for identifying stress and Bovine respiratory disease (BRD). In such applications, measuring temperature for nose and eye region is conducted manually. In this paper, a new automatic method is proposed for extracting the hottest regions from the face region, which may include eyes, nose and mouth. The proposed method involves face detection, thresholding, and blob refinement. The preliminary results show that the proposed algorithm is working well for localization and temperature measurement.
Download

Paper Nr:	26
Title:	Genetic Programming based Synthesis of Clustering Algorithm for Identifying Batches of Electronic Components
Authors:	Evgenii Sopov and Ilia Panfilov
Abstract:	A manufacture of electronic components involves the quality management, but still characteristics of components from different batches may vary. For many highly precise and reliable applications, such as aerospace or military systems, it is necessary to identify and use components from the same batch. This problem is usually stated as a clustering problem or as a k-centroids allocation problem. The k-centroids problem is a generalization of the Fermat–Weber location problem, which is known to be NP-hard. Genetic algorithms have proved their efficiency in solving many hard optimization problems. Genetic algorithms are also used in clustering algorithms for defining initial points of centroids for location-allocation clustering algorithms. At the same time, standard genetic algorithms demonstrates low performance in solving real-world clustering problems, and, as a result, different heuristic-based modifications have been proposed. In this study, we will synthesize a new selection heuristic for a genetic algorithm, which is used for solving the clustering problem of identifying batches of electronic components. We will use a genetic programming based hyperheuristic for creating a selection operator represented by a probability distribution. The results of solving two real-world batch identification problems of microchip manufactures for aerospace applications are presented and are compared with base-line approaches and some previously obtained results.
Download

Paper Nr:	31
Title:	Enhancing Neural Network Prediction against Unknown Disturbances with Neural Network Disturbance Observer
Authors:	Maxime Pouilly-Cathelain, Philippe Feyel, Gilles Duc and Guillaume Sandou
Abstract:	Neural network prediction is a very challenging subject in the presence of disturbances. The difficulty comes from the lack of knowledge about perturbation. Most papers related to prediction often omit disturbances but, in a natural environment, a system is often subject to disturbances which could be external perturbations or also small internal parameters variations caused, for instance, by the ageing of the system. The aim of this paper is to realize a neural network predictor of a nonlinear system; for the predictor to be effective in the presence of varying perturbations, we provide a neural network observer in order to reconstruct the disturbance and compensate it, without any a priori knowledge. Once the disturbance is compensated, it is easier to realize such a global neural network predictor. To reach this goal we model the system with a State-Space Neural Network and use this model, completed with a disturbance model, in an Extended Kalman Filter.
Download

Paper Nr:	68
Title:	A Review of Safety Methods for Human-robot Collaboration and a Proposed Novel Approach
Authors:	Ansuri Reddy, Glen Bright and Jared Padayachee
Abstract:	Industrial robots offer the advantage of flexible manufacturing and increased efficiency when paired with human workers. However, this means breaking well-established safety procedures such as safety fences and workspace separation. Robots present a danger to humans as they work at high speeds with sudden motions. It is therefore necessary to ensure safe interaction during collaboration. This paper presents a collection of sources that explain the trends and advances in the field of industrial robotics specifically to safety in human-robot interaction. Major trends and popular methods lean towards obstacle avoidance using a sensory planning method of polynomials and a sensory system that is able to map the robot workspace. The goal of these methods is to ensure that the human is kept safe. These methods were used to develop a novel approach to safe interactions. This approach uses a LIDAR sensor for obstacle detection and tracking.
Download

Paper Nr:	69
Title:	A Hierarchical Planner based on Set-theoretic Models: Towards Automating the Automation for Autonomous Systems
Authors:	Bernd Kast, Vincent Dietrich, Sebastian Albrecht, G. W. Feiten and Jianwei Zhang
Abstract:	The complexity of today’s autonomous systems renders the manual engineering of control strategies or behaviors for all possible system states infeasible. Therefore, planning algorithms are required that match the capabilities of the system to the tasks at hand. Solutions to typical problems with robotic systems combine aspects of symbolic action planning with sub-symbolic motion planning and control. The problem complexity of this combination currently prohibits online planning without task specific, manually defined heuristics. To counter that we use a set-theoretic approach to model declarative and procedural knowledge which allows for flexible hierarchies of planning tasks. The coordination of the planning tasks on different levels, the classification of information and various views on data are the core functions of hierarchical planning. We propose suitable graph structures to capture all relevant information and discuss the elements of our hierarchical planning algorithm in this paper. Furthermore, we present two use-cases of an autonomous manufacturing system to highlight the capabilities of our system.
Download

Paper Nr:	74
Title:	Improving the Convergence of the Periodic QZ Algorithm
Authors:	Vasile Sima and Pascal Gahinet
Abstract:	The periodic QZ algorithm involved in the structure-preserving skew-Hamiltonian/Hamiltonian algorithm is investigated. These are key algorithms for many applications in diverse theoretical and practical domains such as periodic systems, (robust) optimal control, and characterization of dynamical systems. Although in use for several years, few examples of skew-Hamiltonian/Hamiltonian eigenproblems have been discovered for which the periodic QZ algorithm either did not converge or required too many iterations to reach the solution. This paper investigates this rare bad convergence behavior and proposes some modifications of the periodic QZ and skew-Hamiltonian/Hamiltonian solvers to avoid nonconvergence failures and improve the convergence speed. The results obtained on a generated set of one million skew-Hamiltonian/Hamiltonian eigenproblems of order 80 show no failures and a significant reduction (sometimes of over 240 times) of the number of iterations.
Download

Paper Nr:	78
Title:	Compensation of Mismatched Disturbances for Nonlinear Plants with Distributed Time-delay
Authors:	Igor Furtat, Pavel Gushchin, Dmitrii Konovalov and Sergey Vrazhevsky
Abstract:	The paper deals with the robust algorithm for compensation of unknown mismatched disturbances depending on a state vector of plants with distributed time-delay. The algorithm based on generalization of a backstepping method and disturbance compensation method. The proposed control system compensates disturbances with required accuracy. The simulation results illustrate the efficiency and robustness of the suggested control system. System". MIMO System".
Download

Paper Nr:	83
Title:	The Approach to the Detection of the Movement Precursor by Electromyographic Signals
Authors:	Semen Kurkin, Vladimir Khorev, Elena Pitsik, Vladimir Maksimenko and Alexander Hramov
Abstract:	We have developed a technique allowing automatic detection of the precursor of movement beginning based on the analysis of electromyographic signals. Methods for determining the beginning of movement and the moments of movement planning are of urgent need in neuroscience, and a separate problem is the use of muscle electrical activity signals (electromyograms) to accurately determine the beginning of hand movement due to the complexity, short duration and noise of the original signals. This issue is particularly significant for experiments with simultaneous recording of electroencephalograms, when it is necessary to consider the interaction between the structures of the brain. We have found out that in the case when the movement starts on a certain sound signal, the moment of the movement beginning is detected with a some time delay.
Download

Paper Nr:	101
Title:	Large Deviations in Discrete-time Systems with Control Signal Delay
Authors:	Nina Vunder, Natalia Dudarenko and Valery Grigoriev
Abstract:	The paper considers a problem of deviations (peak effect) in the free motion of linear discrete stable systems with a control signal delay. The problem consists in structure of eigenvectors of the state matrix. The control signal delay adds additional order to a discrete-time model and leads to the variation of eigenvectors structure and deviation increasing in the free motion of the system. A tracking discrete-time system is a subject of the research. An approach to the modal control law design taking into account the value of delay and the deviation is suggested in the paper. It is proposed to assess the upper bound of peaking processes in the system with the condition number of an eigenvectors matrix. The results are supported by an example.
Download

Paper Nr:	109
Title:	Finite Control Augmented with Fuzzy Logic for Automotive Air-spring Suspension System
Authors:	Mohamed E. Shalabi, Haitham El-Hussieny, A. A. Abouelsoud and Ahmed R. Fath Elbab
Abstract:	This paper investigates the spring stiffness control of air suspension systems working under different operating conditions of road profile frequencies and amplitudes. Usually changing the stiffness of the air spring involves variations of the enclosed air pressure by pumping air into or out of the air chamber, or by changing its volume. Since, changing spring stiffness through controlling its pressure consumes power and is not instantaneous, controlling the stiffness through finite volume control is merged with a PI-like Fuzzy Logic Control (PI-FLC) in this paper. This is achieved by connecting the air spring volume to two additional unequal volumes. By controlling the total spring volumes through ON-OFF switching valves, four different stiffness settings are available, and one can achieve an improved performance of air suspension system. A nonlinear quarter-car model is used to evaluate the proposed approach while a Genetic Algorithm (GA) optimization is applied to estimate the PI-FLC optimal gains and the finite levels for switching the spring volumes. Numerical simulations results demonstrate the performance of the proposed control under different road profile. The vehicle body acceleration decreases by a value that reaches 4 cm/s2 which means improving the passenger ride comfort as well as maintaining the passenger safety. This in turns encourages the implementation of the proposed approach on an actual vehicle air suspension in the near future to further verify the system performance.
Download

Paper Nr:	117
Title:	Autonomous Overtaking Maneuver Design based on Follow the Gap Method
Authors:	Munire D. Demir and Volkan Sezer
Abstract:	This paper proposes a solution for one of the most important components of autonomous driving: "overtaking maneuver". Follow the Gap method (FGM) is oneof the most popular obstacle avoidance algorithms and directly obtains steering angle from position of the obstacles around. This paper is the first study using FGM to solve the overtaking problem. Different from previous studies where a trajectory is planned and then a controller is designed to track it; we use FGM for motion planning and control together. This paper focuses on overtaking maneuver in a challenging environment like highway traffic where the safety and fast response are the key factors. After we adapt the FGM to overtaking problem, we compare it with an existing overtaking method X-sin functions from literature. Since X-sin functions method requires a path tracker (controller), Stanley method is combined with X-sin functions. At the end of this work, we show several advantages of FGM comparing to the X-sin functions based overtaking approach.
Download

Paper Nr:	120
Title:	Water-resource Optimization Problem of Inland Waterways based on Network Flows with Flow Transition Time and Time Varying Characteristics
Authors:	Eric Duviella, Baya Hadid and Débora S. Alves
Abstract:	Water-resource allocation planning is a well studied problem that aims at sharing water-resource to answer to multi-objective management. For inland waterways, water-resource has to be balanced among the networks to guaranty navigation conditions as a priority. Hydraulic devices such as locks and gates are used to transfer volumes of water between the interconnected navigation reaches that composed the network. By considering a large spatial scale with a low control time scale, transport delays have to be considered. Hence, network flows with flow transition time and time varying characteristics is proposed to deal with transport delays and modifications of the operating conditions over time. Network flows are then used for the optimization step. The proposed model and optimization approach are illustrated by considering an inland waterway that is composed of two navigation reaches.
Download

Paper Nr:	124
Title:	Neuroevolution with CMA-ES for Real-time Gain Tuning of a Car-like Robot Controller
Authors:	Ashley Hill, Eric Lucet and Roland Lenain
Abstract:	This paper proposes a method for dynamically varying the gains of a mobile robot controller that takes into account, not only errors to the reference trajectory but also the uncertainty in the localisation. To do this, the covariance matrix of a state observer is used to indicate the precision of the perception. CMA-ES, an evolutionary algorithm is used to train a neural network that is capable of adapting the robot’s behaviour in real-time. Using a car-like vehicle model in simulation. Promising results show significant trajectory following performances improvements thanks to control gains fluctuations by using this new method. Simulations demonstrate the capability of the system to control the robot in complex environments, in which classical static controllers could not guarantee a stable behaviour.
Download

Paper Nr:	128
Title:	Intelligent Distributed System for Indoor Heat Flow Control
Authors:	Y. S. Nurakhov, B. Bektugan, K. Nurbergen, T. S. Imankulov and D. Z. Akhmed-Zaki
Abstract:	In this paper, we consider the software and hardware implementation of an intelligent distributed system for forecasting and controlling the optimal distribution of heat in the room. Prediction is based on a pre-trained neural network model. The system uses calculation results of the one-dimensional heat conduction problem to correct neural model being trained and decides to turn on / off a specific air conditioner depending on the predicted data.
Download

Paper Nr:	134
Title:	Home Automation System for People with Visual and Motor Disabilities in Colombia
Authors:	William Coral, Alvaro Alarcon, Jose Llanos and Jose Hernandez
Abstract:	In this paper we present the development of a home automation system based on a Smartphone with touch to speech feedback. The purpose was to solving problems of accessibility and comfort inside homes for people with visual disabilities. The technological design was based on the development of a web server using an Arduino Uno and a Wi-Fi Shield. The router connects the smartphone to the web server. Then a router connects a smartphone to the server to receive information about the home location and send control signals for power up the household appliances. The tests were performed on people with visual disabilities and people with motor disabilities.
Download

Paper Nr:	138
Title:	Evolutionary Split Range Controller for a Refrigeration System
Authors:	Gerardo A. Soto and Jesús-Antonio Hernandez-Riveros
Abstract:	Every year more than 80 million units of domestic refrigerators are produced worldwide. Hundreds of millions are used continuously so the impact on electricity is significant. Typical initiatives in energy efficiency for refrigeration systems are aimed at: a) redesigns b) new materials and c) good use practices. A different approach in energy efficiency for Vapour Compression Refrigeration Systems (VCRS) is the implementation of control strategies that directly reduce energy consumption while guaranteeing operating conditions. The difficulty lies in the multiple energy domains of the system (electric/mechanical/hydraulic/thermal), high coupling, multiplicity of variables, strong non-linearity and non-stationary regime. This paper focuses on increasing the energy efficiency of a VCRS with the implementation of an optimal split range and multi-objective evolutionary control. The evolutionary control is expanded to variable speed compressors and electronic expansion valves. The effectiveness of the evolutionary method was demonstrated through the Benchmarking of the IFAC. Now, in the multi-domain model of the VCRS, the MAGO algorithm is applied to optimally tune a split range controller to achieve a more precise behaviour and multi-objective to save energy. The cases studied go from traditional control to multivariable and multivariable-multi-objective control, the results in energy saving are outstanding.
Download

Paper Nr:	156
Title:	Leveraging Cloud-based Tools to Talk with Robots
Authors:	Enas Altarawneh and Michael Jenkin
Abstract:	Although there has been significant advances in human-machine interaction systems in recent years, cloud-based advances are not easily integrated in autonomous machines. Here we describe a toolkit that supports interactive avatar animation and modeling for human-computer interaction. The avatar toolkit utilizes cloud-based speech-to-text software that provides active listening by detecting sound and reducing noise, a cloud-based AI to generate appropriate textual responses to user queries, and a cloud-based text-to-speech generation engine to generate utterances for this text. This output is combined with a cloud-based 3D avatar animation synchronized to the spoken response. Generated text responses are embedded within an XML structure that allows for tuning the nature of the avatar animation to simulate different emotional states. An expression package controls the avatar’s facial expressions. Latency is minimized and obscured through parallel processing in the cloud and an idle loop process that animates the avatar between utterances.
Download

Paper Nr:	159
Title:	Structure and Parameter Identification of Process Models with Hard Non-linearities for Industrial Drive Trains by Means of Degenerate Genetic Programming
Authors:	Mathias Tantau, Lars Perner, Mark Wielitzka and Tobias Ortmaier
Abstract:	The derivation of bright-grey box models for electric drives with coupled mechanics, such as stacker cranes, robots and linear gantries is an important step in control design but often too time-consuming for the ordinary commissioning process. It requires structure and parameter identification in repeated trial and error loops. In this paper an automated genetic programming solution is proposed that can cope with various features, including highly non-linear mechanics (friction, backlash). The generated state space representation can readily be used for stability analysis, state control, Kalman filtering, etc. This, however, requires several special rules in the genetic programming procedure and an automated integration of features into the defining state space form. Simulations are carried out with industrial data to investigate the performance and robustness.
Download

Paper Nr:	165
Title:	Automatic Offset Detection in GPS Time Series by Change Point Approach
Authors:	Giuseppe Nunnari and Flavio Cannavo
Abstract:	This paper deals with the problem of automatic detection of offsets in GPS time series, which is of interest both in active volcanic and tectonic areas, where they often signal either the opening of eruptive fissures or seismic and aseismic dislocations. The problem is tackled by using the Change Point Detection (CPD) approach. Results show that CPD algorithms are suitable both in off-line and on-line frameworks. In particular, we show that CPD algorithms could contribute to the implementation of a warning system of volcanic intrusive activity.
Download

Paper Nr:	166
Title:	Asynchronous Control Design of Continuous-time Markovian Jump Systems with Bounded Time-varying Transition Rates
Authors:	Ngoc A. Nguyen and Sung H. Kim
Abstract:	The asynchronous control design of continuous-time Markovian jump systems with bounded time-varying transition rates is addressed in this paper. According to the framework of parameterized linear matrix inequalities (PLMIs), essential stabilization conditions are established with consideration on dissipativity performance and then transform to solvable sets of linear matrix inequalities (LMIs) under our proposed method. Especially, our technique is derived from not only time-varying system modes but also asynchronous control modes transition rates. The effectiveness of our method is then illustrated through our numerical example.
Download

Paper Nr:	168
Title:	Class-based Storage Location Assignment: An Overview of the Literature
Authors:	Behnam Bahrami, Hemen Piri and El-Houssaine Aghezzaf
Abstract:	Storage, per se, is not only an important process in a warehouse, also it has the greatest influence on the most expensive one, i.e., order picking. This study aims to give a literature overview on class-based storage location assignment (CBSLAP). In this paper, we discuss storage policies and present a classification of storage location assignment problem. Next, different configuration of classes are presented. We identify the research gaps in the literature and conclude with promising future research directions.
Download

Paper Nr:	169
Title:	Detecting Domain-specific Events based on Robot Sensor Data
Authors:	Bernhard G. Humm and Guglielmo van der Meer
Abstract:	This paper presents an approach for detecting domain-specific events based on robot sensor data. Events may be error situations as well as successfully executed manufacturing steps, depending on the application domain at hand. The approach includes segmenting streams of sensor data into meaningful intervals and subsequently matching patterns on those segments. Pattern matching is performed in near real-time allowing events to be detected continuously during the execution of a robotics application. The approach is demonstrated by means of a real-world manufacturing use case, namely the automated assembly of electrical components by a robot. The approach has been implemented prototypically had has been evaluated successfully.
Download

Paper Nr:	172
Title:	Towards Automated Parameter Optimisation of Machinery by Persisting Expert Knowledge
Authors:	Richard Nordsieck, Michael Heider, Andreas Angerer and Jörg Hähner
Abstract:	Commissioning of machines takes up a considerable share of time and money of the total cost of developing a machine. Our project aims at developing an approach to decrease the time needed to commission machines by automating parameter optimisation with the help of formalised expert knowledge. The approach will be developed on the Fused Deposition Modelling (FDM) process, which is an additive manufacturing technique. We pay particular attention to keeping the approach sufficiently abstract to be applied to machines from other domains to benefit its industrial application.
Download

Paper Nr:	173
Title:	Motor-less and Gear-less Robots: New Technologies for Service and Personal Robots
Authors:	Claudio Rossi, William Coral and Julian Colorado
Abstract:	In the last years, we have been working on exploring alternative actuation technologies for the future service and personal robots. These shall allow designing lighter and safer robots, devoid of conventional mechanical transmission mechanisms i.e. motor-less and gear-less robots. Here, we summarise our work with Shape Memory Alloys. We show that, despite their known limitations, by finding suitable niches of application, dedicated mechatronics design, and ad-hoc control strategies, SMAs can effectively be used as an alternative actuation technology for robotic systems.
Download

Paper Nr:	175
Title:	Hybrid DDPG Approach for Vehicle Motion Planning
Authors:	Árpád Fehér, Szilárd Aradi, Ferenc Hegedűs, Tamás Bécsi and Péter Gáspár
Abstract:	The paper presents a motion planning solution which combines classic control techniques with machine learning. For this task, a reinforcement learning environment has been created, where the quality of the fulfilment of the designed path by a classic control loop provides the reward function. System dynamics is described by a nonlinear planar single track vehicle model with dynamic wheel mode model. The goodness of the planned trajectory is evaluated by driving the vehicle along the track. The paper shows that this encapsulated problem and environment provides a one-step reinforcement learning task with continuous actions that can be handled with Deep Deterministic Policy Gradient learning agent. The solution of the problem provides a real-time neural network-based motion planner along with a tracking algorithm, and since the trained network provides a preliminary estimate on the expected reward of the current state-action pair, the system acts as a trajectory feasibility estimator as well.
Download

Paper Nr:	178
Title:	Air-coupled Ultrasonic Inspection with Adaptive Lamb Wave Control
Authors:	Manfred Schönheits, Armin Huber and Philipp Gänswürger
Abstract:	Single-sided air-coupled ultrasonic inspection has some beneficial properties compared to water-coupled ultrasonic inspection or double-sided ultrasonic testing. The absence of the need for water leads to easier process handling on the one hand e.g. when manufacturing aircraft components. On the other hand, because the process is single-sided, reachability is a minor problem compared to double-sided testing and end-effectors and fixtures can be designed in a less complex and more compact way. However, the nature of lamb waves requires that the geometrical relation of the transmitter and the receiver varies during the inspection process. In this paper, a prototype of an adaptive end-effector is introduced that was developed to implement this requirement and results of first evaluation tests are presented.
Download

Paper Nr:	196
Title:	Distributing Intelligence among Cloud, Fog and Edge in Industrial Cyber-physical Systems
Authors:	Jonas Queiroz, Paulo Leitão, José Barbosa and Eugénio Oliveira
Abstract:	The 4th industrial revolution advent promotes the reorganization of the traditional hierarchical automation systems towards decentralized Cyber-Physical Systems (CPS). In this context, Artificial Intelligence (AI) can address the new requirements through the use of data-driven and distributed problem solving approaches, such those based on Machine-Learning and Multi-agent Systems. Although their promising perspectives to enable and manage intelligent Internet of Things environments, the traditional Cloud-based AI approaches are not suitable to handle many industrial scenarios, constrained by responsiveness and data sensitive. The solution lies in taking advantage of Edge and Fog computing to create a decentralized multi-level data analysis computing infrastructure that supports the development of industrial CPS. However, this is not a straightforward task, posing several challenges and demanding new approaches and technologies. In this context, this work discusses the distribution of intelligence along Cloud, Fog and Edge computing layers in industrial CPS, leveraging some research challenges and future directions.
Download

Paper Nr:	200
Title:	Optimal Control to Limit the Propagation Effect of a Virus Outbreak on a Network
Authors:	Paolo Di Giamberardino and Daniela Iacoviello
Abstract:	The aim of this paper is to propose an optimal control strategy to face the propagation effects of a virus outbreak on a network; a recently proposed model is integrated and analysed. Depending on the specific model caracteristics, the epidemic spread could be more or less dangerous leading to a virus free or to a virus equilibrium. Two possible controls are introduced: a test on the computers connected in a network and the antivirus. In a condition of limited resources the best allocation strategy should allow to reduce the spread of the virus as soon as possible.
Download

Paper Nr:	201
Title:	Fault Diagnosis by Bayesian Network Classifiers with a Distance Rejection Criterion
Authors:	M. A. Atoui, Achraf Cohen, Phillipe Rauffet and Pascal Berruet
Abstract:	In this paper, Bayesian network classifiers (BNCs) are used as a statistical tool to diagnosis faults with a distance rejection criterion. The proposed approach enhances significantly the structure of the use of Bayesian networks in the same context. Our framework is evaluated and compared to state of the art using data from the benchmark Tennessee Eastman Process (TEP).
Download

Paper Nr:	9
Title:	The Modeling, Construction and Test Process of a 3D Printable Smart Robot Rider
Authors:	João M. Gorte Jr., Witenberg R. Souza, Artur B. Coelho and Lí E. López
Abstract:	This work aims to present a modeling procedure, manufacturing process, electronic design, programming and communication system of a cyclist robot. The robot rider has the ability to ride a bicycle independently by making decisions on shifts in balance that may occur during its motion by correcting its direction, balance adjust, and stop. Robot decision-making processes were embedded in a shared control system of interactions with the external environment by commands sent through wired serial link or radio frequency(RF), allowing arm and leg-movements. This was achieved using a dual board synchronization powered by Atmel microcontrollers (Arduino) and fed by information from an electronic gyroscope sensor, an accelerometer, and remote radio frequency (RF) receptor. The final prototype was able to pedal from inertia accelerating gradually to its full speed, stop the movement, and move its arms to recover balance.
Download

Paper Nr:	18
Title:	Smith Predictor for Control of the Temperature Process with Long Dead Time
Authors:	Nikolajs Bogdanovs, Romualds Belinskis, Andris Krūminš, Ernests Petersons and Aleksandrs Ipatovs
Abstract:	The analysis of a problem of development of control systems for objects with big time delay is carried out in this work. For such objects it is difficult to provide high-quality control, because the control is carried on the last status of object’s output. The main setup methods of PID regulators have been examined. Based on this analysis the technique of complete synthesis of the regulator of higher level is given in order to regulate building’s heating system. This work offers a new method of object’s control with distributed delay. As the test bed for the offered structure of control the valve of hot water supply in a heat-node is used. Using the test bed the stability of the system with time delay have been studied, which is controlled by the PID regulator assisted by Smith Predictor used to compensate the dead time.
Download

Paper Nr:	39
Title:	Microgrid Modeling Approaches for Information and Energy Fluxes Management based on PSO
Authors:	Li Qiao, Rémy Vincent, Mourad Ait-Ahmed and Tang Tianhao
Abstract:	In order to improve the reliability, stability and economy of power supply of a microgrid, some fundamental work on microgrid energy management method is carried out. Firstly, models of microgrid components under steady state are established in MATLAB/SIMULINK. Secondly, an operation cost function of microgrid is proposed, together with the constraint conditions. Then, in order to solve the energy management problem, Particle Swarm Optimization (PSO) is declared by using m-files programming. The algorithm will be explained in chart flow and pseudo code. Finally, a simulation scenario is designed to show the good performance of this control method.
Download

Paper Nr:	45
Title:	Check-in Counters Management: The Case Study of Lisbon Airport
Authors:	Ludovica Adacher and Marta Flamini
Abstract:	In this paper the problem of assigning check-in counters to flights in a Zone of Lisbon airport is addressed at an early stage. Real traffic scenario and simulation of passengers behaviour and characteristics are considered. The aim is to minimize an objective function that takes into consideration the managing cost of opening check-in counters and the passengers’ cost of waiting to be served by the check-in operator. This latter cost function has been modelled by considering the International Air Transport Association level of service perceived by the passengers. Since the performances depend on the passengers’ behaviour and characteristics, simulation is used to compute the value of the objective function. Two optimization heuristic procedures have been tested and their results compared.
Download

Paper Nr:	67
Title:	ANFIS based IMC PID Controller for Permanent Magnet DC Motor
Authors:	M. Alasvandi, S. Z. Moussavi, E. Morad and E. Rasouli
Abstract:	Permanent Magnet Direct Current (PMDC) motors are widely used in industrial application and PID controllers are usually applied to improve performance characteristics of PMDC motor. There are different methods for setting up PID parameters that one of them has been called Internal Model Control (IMC) which is used λ parameter to modify performance characteristics of system. Sometimes setting up IMC PID parameters are hard so in this paper, ANFIS is used to add proper values with IMC PID coefficients. The proposed controller used ANFIS based coefficient modifier because it can train easily and help system to achieve desired performance characteristics. The proposed system used the fuzzy system that is extracted from training ANFIS system with desired data to improve PMDC motor performance. In this paper IMC based controller is compared with proposed strategy and simulation results shows that proposed control system have acceptable characteristic in different situation such as no-load, applied-load, changing reference speed and it is effective methods to control system in noisy condition.
Download

Paper Nr:	133
Title:	Electronic Voting System for Universities in Colombia
Authors:	Jose Llanos, William Coral, Alvaro Alarcon, Juan Cruz and Jhojan Ramirez
Abstract:	In this manuscript we present the development of Electronic Voting System (EVS) for the elections process at universities in Colombia. This application is based on the architectural pattern Model View Controller (MVC) and Open Web Application Security Project (OWASP) by defining five risk associated to the security of the system. During the development of this software we performed a wide range of usability tests and response times. This allowed to improve the performance of this software in its execution and delivery of results. We conclude that the use of this type of applications allows to obtain the results quickly and accurately and the process of recount votes is eliminated and the costs of executing the electoral process are reduced.
Download

Paper Nr:	144
Title:	PARADA: Control Support System for Parades
Authors:	José E. Lima, Pedro M. Faria and Pedro M. Moreira
Abstract:	The parade of “Festas in honor of Nossa Senhora D’Agonia”, which is celebrated every year in the city of Viana do Castelo, it is one of the highlights of the traditional festival, that gathers hundreds of people in one giant parade throughout the city streets, this event attracts thousands of spectators. Due to its big dimension, it presents some difficulties regarding its organization. The lack of cohesion of the parade during its course is one of the issues observed that originates several and large empty spaces, which end up to discredit the parade. This paper presents the study the issue related with the Parade’s organization/planning, by proposing a solution based on low-cost technologies. In this work we intend to study the problem of empty spaces, proposing a solution based on low cost technologies and evaluating the performance of this solution with its potential users. In this way, a process of collect information was initiated through the observation of the Parade, an interview with the organization and an inquiry of the collaborators and another one for the drivers. Based on the collected information, it is proposed a solution that uses smartphones to interconnect through a mobile application and also a web management application, in order to monitor the Parade and help in suppressing empty spaces. The proposal was evaluated to its potential users through a functional prototype. Usability and User Experience tests were performed and the results were promising. It is intended to validate the proposed solution in the field and extend the proposal to other Parade.
Download

Paper Nr:	183
Title:	Nonlinear Data-driven Process Modelling using Slow Feature Analysis and Neural Networks
Authors:	Jeremiah Corrigan and Jie Zhang
Abstract:	Slow feature analysis is a technique that extracts slowly varying latent variables from a dataset. These latent variables, known as slow features, can capture underlying dynamics when applied to process data, leading to improved generalisation when a data-driven model is built with these slow features. A method utilising slow feature analysis with neural networks is proposed in this paper for improving generalisation in nonlinear dynamic process modelling. Additionally, a method for selecting the number of dominant slow features using changes in slowness is proposed. The proposed method is applied to creating a soft sensor for estimating polymer melt index in an industrial polymerisation process to validate the method’s performance. The proposed method is compared with principal component analysis-neural network and a neural network without any latent variable method. The results from this industrial application demonstrate the effectiveness of the proposed method for improving model generalisation capability and reducing dimensionality.
Download

Area 3 - Robotics and Automation

Full Papers

Paper Nr:	20
Title:	Camera and Lidar Cooperation for 3D Feature Extraction
Authors:	Burtin Gabriel, Bonnin Patrick and Malartre Florent
Abstract:	The objective of this work is to use efficiently various sensors to create a SLAM system. This algorithm has to be fast (real-time), computationally light and efficient enough to allow the robot to navigate in the environment. Because other processes embedded require large amount of cpu-time, our objective was to use efficiently complementary sensors to obtain a fairly accurate localization with minimal computation. To reach this, we used a combination of two sensors: a 2D lidar and a camera, mounted above each other on the robot and oriented toward the same direction. The objective is to pinpoint and cross features in the camera and lidar FOV. Our optimized algorithms are based on segments detection. We decided to observe intersections between vertical lines seen with the camera and locate them in 3D with the ranges provided by the 2D lidar. First we implemented a RGB vertical line detector using RGB gradient and linking process, then a lidar data segmentation with accelerated computation and finally we used this feature detector in a Kalman filter. The final code is evaluated and validated using an advanced real-time robotic simulator and later confirmed with a real experiment.
Download

Paper Nr:	25
Title:	Balancing Control of a Self-driving Bicycle
Authors:	T. J. Yeh, Hao-Tien Lu and Po-Hsuan Tseng
Abstract:	In this research, a self-driving bicycle is constructed and the balancing control using the handlebar is studied. The controller is designed based on a model which characterizes the bicycle’s lateral dynamics under speed variations. As the model can be decomposed into a convex combination of four linear subsystems with time-varying coefficients, the proposed controller also consists of a convex combination of four linear, full-state feedback controllers. It is proved that if the full-state feedback controllers satisfy a set of linear matrix inequalities, the bicycle can maintain its lateral stability regardless of speed changes. Both simulations and experiments verify that the proposed controller can achieve robust balancing performance under various operating conditions.
Download

Paper Nr:	40
Title:	Singularity Analysis for Redundant Manipulators of Arbitrary Kinematic Structure
Authors:	Ahmad A. Almarkhi and Anthony A. Maciejewski
Abstract:	This paper presents a technique to identify singularities of any rank for a robot of any kinematic structure. The technique is based on computing the gradient of singular values of the robot Jacobian. The algorithm deals with the situations when two or more singular values become nearly equal and their corresponding singular vectors are ill-defined. Also, an algorithm is developed to identify the physically meaningful singular directions from the high dimensional singular subspaces of high-rank singularities. The suggested technique is applied to a 4-DoF and a 7-DoF robot to show its efficacy at identifying robot singularities of all ranks and dealing with the ill-defined singular directions.
Download

Paper Nr:	41
Title:	Automated Draping of Wide Textiles on Double Curved Surfaces
Authors:	Patrick Kaufmann, Georg Braun, Andreas Buchheim and Marcin Malecha
Abstract:	In many different industries like aviation, shipbuilding or the production of wind turbines, the draping of textiles is a common issue. Especially large components in long- and medium-haul aircraft have a high potential of weight reduction by using composites. In many cases increasing material and manufacturing costs are caused compared to metal design. Therefore automation is one approach to achieve profitability. A robot end effector for the automated deposition of 50 inch wide fibre fabrics was tested. The experiments were performed in full scale, with plies of an aircraft pressure bulkhead. When depositing these fabrics on curved surfaces, defects such as waves or wrinkles appear. In order to solve this issue, the end effector was extended by adding an adaptable material buffer. The development regarding mechanical design, calculation for determining the axis movement as well as the axes control is presented. Compared to previous attempts without an adaptable material buffer, an improved deposition quality was achieved. The results of the experimental investigation are shown.
Download

Paper Nr:	42
Title:	Hybrid Force/Position Control of a Very Flexible Parallel Robot Manipulator in Contact with an Environment
Authors:	Fatemeh Ansarieshlaghi and Peter Eberhard
Abstract:	There are many applications for robot manipulators and these tasks are complicated when they have interaction with environments and humans. This paper investigates a novel strategy to control a very flexible parallel manipulator interacting with an environment. The controller is complicated when the used robot manipulator is a flexible multibody dynamics system and the flexibility shall be taken into account in the modeling and controlling process. Also, interaction with an unknown environment is another challenge of our research. Hence, a sophisticated controller is designed to overcome the respective challenges. To this end, a hybrid force/position control strategy is utilized. Therefore, two controllers based on the rigid and flexible models of the robot are designed and implemented to interact with a surface. The simulation results show that the controllers based on the flexible model have a better performance than those based on the rigid model and successfully track a trajectory and interact with an environment.
Download

Paper Nr:	43
Title:	Optimum Design and FEA of a Hybrid Parallel-deployable Structure-based 3-DOF Multi-gripper Translational Robot for Field Pot Seedlings Transplanting
Authors:	Samy M. Assal and Isaac Ndawula
Abstract:	Pot seedlings transplanting is an activity in the agricultural production industry. In its manual level, it is a time consuming, labour intensive, costly activity with low transplanting rate, uneven plant distribution and low degree of accuracy. So, in this paper, a novel partially decoupled 3-DOF multi-gripper pot seedlings transplanting robot is proposed to be used in the open agricultural field to increase the transplanting rate. The proposed robot is composed of two identical 2-DOF Diamond Delta robots, 1-DOF scissor mechanism and belt conveyor. Delta robot is a high speed parallel robot that is used to control the grippers in the X-Z plane while the scissor mechanism is a deployable structure that is worked in the multi-gripper and used to control the grippers in Y direction. Different kinematic and design aspects are considered; namely, the kinematic analysis and the optimum design as well as the finite element analysis in the most critical loading configuration are carried out. A unified frame work for the optimum dimensional synthesis for a prescribed workspace with force transmission and singularity avoidance constraints is developed for the optimal dimensions of the design parameters. The proposed robot is shown to have high transplanting rate and is safe in terms of stress and deformation.
Download

Paper Nr:	58
Title:	A Fuzzy Inference Approach to Control Robot Speed in Human-robot Shared Workspaces
Authors:	Angelo Campomaggiore, Marco Costanzo, Gaetano Lettera and Ciro Natale
Abstract:	Nowadays, human-robot collaboration (HRC) is an important topic in the industrial sector. According to the current regulations, the robot no longer needs to be isolated in a work cell, but a collaborative workspace in which human operators and robots coexist can be acceptable. Human-robot interaction (HRI) is made possible by proper design of the robot and by using advanced sensors with high accuracy, which are adopted to monitor collaborative operations to ensure the human safety. Goal of this article is to implement a fuzzy inference system, based on the ISO/TS 15066, to correctly compute the minimum protective separation distance and adjust the robot speed by considering different possible situations, with the aim to avoid any collisions between operators and robots trying to minimize cycle time as well.
Download

Paper Nr:	71
Title:	Environment-aware Sensor Fusion using Deep Learning
Authors:	Caio F. Silva, Paulo K. Borges and José C. Castanho
Abstract:	A reliable perception pipeline is crucial to the operation of a safe and efficient autonomous vehicle. Fusing information from multiple sensors has become a common practice to increase robustness, given that different types of sensors have distinct sensing characteristics. Further, sensors can present diverse performance according to the operating environment. Most systems rely on a rigid sensor fusion strategy which considers the sensors input only (e.g., signal and corresponding covariances), without incorporating the influence of the environment, which often causes poor performance in mixed scenarios. In our approach, we have adjusted the sensor fusion strategy according to a classification of the scene around the vehicle. A convolutional neural network was employed to classify the environment, and this classification is used to select the best sensor configuration accordingly. We present experiments with a full-size autonomous vehicle operating in a heterogeneous environment. The results illustrate the applicability of the method with enhanced odometry estimation when compared to a rigid sensor fusion scheme.
Download

Paper Nr:	77
Title:	Aerial Monitoring of Rice Crop Variables using an UAV Robotic System
Authors:	C. Devia, J. Rojas, E. Petro, C. Martinez, I. Mondragon, D. Patino, C. Rebolledo and J. Colorado
Abstract:	This paper presents the integration of an UAV for the autonomous monitoring of rice crops. The system integrates image processing and machine learning algorithms to analyze multispectral aerial imagery. Our approach calculates 8 vegetation indices from the images at each stage of rice growth: vegetative, reproductive and ripening. Multivariable regressions and artificial neural networks have been implemented to model the relationship of these vegetation indices against two crop variables: biomass accumulation and leaf nitrogen concentration. Comprehensive experimental tests have been conducted to validate the setup. The results indicate that our system is capable of estimating biomass and nitrogen with an average correlation of 80% and 78% respectively.
Download

Paper Nr:	80
Title:	A Generic Control Framework for Mobile Robots Edge Following
Authors:	Mathieu Deremetz, Adrian Couvent, Roland Lenain, Benoit Thuilot and Christophe Cariou
Abstract:	In this paper, the problem associated with accurate control for mobile robots following an edge is addressed thanks to a backstepping control. In particular, the control of the angular speed (control input) is investigated through the derivation of a new backstepping control by gathering derivatives regarding to time and to the curvilinear abscissa in a single framework. This new reference then allows both time and distance convergence of the robot states towards a trajectory computed with points given by a Lidar only. This permits to address the control of different kinds of robots (skid-steering, car like, four-wheel-steering) in a common framework and to consider independently the speed regulation, the lateral and the longitudinal controls. The control proposed here allows an accurate and reactive path tracking even if the environment is complex and narrow. The efficiency of the approach is investigated through full scale experiments in various conditions.
Download

Paper Nr:	81
Title:	Kinematics Modelling, Optimization and Control of Hybrid Robots
Authors:	Mahmoud Tarokh and Federico Llenar
Abstract:	The paper develops a unified kinematics modelling, optimization and control for hybrid robots. These robots combine two or more modes of operations, such as a combination of walking and rolling, or rolling and manipulation. The equations of motion are derived in compact forms that embed an optimization criterion. These equations are used to obtain various useful forms of the robot kinematics. Using the developed modelling, actuation and control equations are derived that ensure the robot to track a desired path closely while maintaining balanced operations and tip-over avoidance. Various simulation results are provided for a hybrid rolling-walking robot traversing uneven terrain, which demonstrate the capabilities and effectiveness of the developed methodologies.
Download

Paper Nr:	143
Title:	Optimal Waypoint Navigation for Underactuated Cruising AUVS
Authors:	Kangsoo Kim
Abstract:	An advanced approach to the waypoint-based navigation for near-bottom survey of a cruising AUV is presented. Pursuing vehicle safety as well as high-definition bottom survey data, we apply GDS-based optimization technique for achieving waypoint-based minimum-altitude flight of an underactuated cruising AUV. While the objective of our optimization is minimizing average altitude of a vehicle throughout its flight interval, depth or altitude references on waypoints are used as control inputs. In our optimization, bottom bathymetry is incorporated as a constraint used for bottom collision avoidance. As another constraint, dynamic model of an AUV is included. By solving the dynamic model in time domain, motion responses of the vehicle following reference waypoints are derived. Our approach of the optimal waypoint navigation is validated by not only simulation but also actual at-sea deployment of an AUV.
Download

Paper Nr:	150
Title:	Combining Onthologies and Behavior-based Control for Aware Navigation in Challenging Off-road Environments
Authors:	Patrick Wolf, Thorsten Ropertz, Philipp Feldmann and Karsten Berns
Abstract:	Autonomous navigation in off-road environments is a challenging task for mobile robots. Recent success in artificial intelligence research demonstrates the suitability and relevance of neural networks and learning approaches for image classification and off-road robotics. Nonetheless, meaningful decision making processes require semantic knowledge to enable complex scene understanding on a higher abstraction level than pure image data. A promising approach to incooperate semantic knowledge are ontologies. Especially in the off-road domain, scene object correlations heavily influence the navigation outcome and misinterpretations may lead to the loss of the robot, environmental, or even personal damage. In the past, behavior-based control systems have proven to robustly handle such uncertain environments. This paper combines both approaches to achieve a situation-aware navigation in off-road environments. Hereby, the robot’s navigation is improved using high-level off-road background knowledge in form of ontologies along with a reactive, and modular behavior network. The feasibility of the approach is demonstrated within different simulation scenarios.
Download

Paper Nr:	214
Title:	Clustering-based Model for Predicting Multi-spatial Relations in Images
Authors:	Brandon Birmingham and Adrian Muscat
Abstract:	Detecting spatial relations between objects in an image is a core task in image understanding and grounded natural language. This problem has been addressed in cognitive linguistics through the development of template and computational models from controlled experimental data using 2D or 3D synthetic diagrams. Furthermore, the Computer Vision (CV) and Natural Language Processing (NLP) communities developed machine learning models for real-world images mostly from crowd-sourced data. The latter models treat the problem as a single label classification problem, whereas the problem is inherently a multi-label problem. In this paper, we learn a multi-label model based on computed spatial features. We choose to implement the model using a clustering-based approach, since apart from predicting multi-labels for a given instance, this method would allow us to get deeper insights into how spatial relations are related to each other. In this paper, we report our results from this model and a direct comparison with a Random Forest single label classifier is presented. The proposed model shows that in general it outperforms the single label classifier even when considering the top four prepositions predicted by the single label classifier.
Download

Short Papers

Paper Nr:	13
Title:	Smart Wheelchairs: Using Robotics to Bridge the Gap between Prototypes and Cost-effective Set-ups
Authors:	Matthew Aquilina, Marvin K. Bugeja and Simon G. Fabri
Abstract:	Wheelchairs have improved the lives of many people with limited mobility. Yet, to this day, conventional wheelchairs are still not a viable option for mobility independence in cases of people with severe weakness or poor coordination e.g. Amyotrophic Lateral Sclerosis (ALS). Smart wheelchairs (SWs) overcome many of these limitations by adding an extra layer of intelligence to the system. SWs have so far remained mostly inaccessible to the general public, due to a limited market presence and steep costs. This paper thus presents the design and implementation of a novel SW which makes the upgrade of a commercially available motorised wheelchair to a SW a much simpler process. The system is a complete implementation offering low-level hardware control, a specialised ROS architecture and autonomous navigation algorithms allowing shared user control or fully-autonomous movement. Contrary to most other published works, the focus of this paper is to implement a fully-featured working prototype with minimal hardware complexity and an efficient modular software development environment. Initial practical tests in typical use scenarios showcased the successful operation of the complete system. The developed prototype SW has the potential to restore autonomy to people who are unable to use conventional or powered wheelchairs.
Download

Paper Nr:	28
Title:	A Comparison Study on Coupling Effects in Balance Control Methods of Humanoid Robots through an Extended Task Space Formulation
Authors:	Seungjae Yoo, Joonhee Jo and Yonghwan Oh
Abstract:	Even though several control methods on the task space dynamics of humanoids have been proposed, they cannot cover the entire dynamics of the system since there are hidden null space dynamics due to kinematic redundancy. Besides, there are few studies on the coupling effects between task space and null space dynamics. Through an extended task space formulation, the coupling effects between each space are manifested because this form allows representing the entire system dynamics. Moreover, by using an adequate selection of weighting matrices, the coupling effects can be inertially decoupled. Regarding the effectiveness of the decoupling process, two whole-body control approaches and provide their mathematical comparisons is proposed. A kinematically decomposed control approach without the decoupling process is first introduced, and its extension to an inertially decoupled control approach is then developed. Furthermore, conventional operational space-based control is discussed to compare the above control approaches. This paper constructs a mathematical analysis of their relationships. Finally, simulation results are given in this paper to demonstrate the validity of the mathematical analysis.
Download

Paper Nr:	32
Title:	Robust Finite-time Position and Attitude Tracking of a Quadrotor UAV using Super-Twisting Control Algorithm with Linear Correction Terms
Authors:	Yassine Kali, Jorge Rodas, Maarouf Saad, Raul Gregor, Walid Alqaisi and Khalid Benjelloun
Abstract:	This work investigates the problem of finite-time position and attitude trajectory of quadrotor unmanned aerial vehicle systems based on a modified second order sliding mode algorithm. The selected algorithm is a modified super-twisting with both nonlinear and linear correction terms. It ensures robustness against unknown dynamics and perturbations and allows fast finite-time convergence even when the trajectories of the considered system are far from the user-chosen switching surface. In addition, this algorithm is very attractive since it solves the major problems of the first and second order sliding mode, namely, the chattering phenomenon and the required unavailable information for practical implementation. To show the effectiveness of the used modified structure of the super-twisting algorithm, simulation results are presented for the considered quadrotor system.
Download

Paper Nr:	44
Title:	Towards an Advanced ROS Package Generator
Authors:	Anthony Remazeilles and Jon Azpiazu
Abstract:	This paper describes a tool for generating ROS packages and nodes. Compared to the relatively basic traditional package creation method, this tool can generate a whole node structure, including its life-cycle and the exposed interface to other ROS nodes. Following a separation of concerns, the developer only defines the interaction means in a XML file, and the tool provides the whole skeleton of the nodes, including the interface creation and management. This way, the developer can focus on his real added value, the implementation of the node logic. Compared to advanced node management frameworks proposed in literature, the tool proposed does not require the developer to understand and agree on complex high-level architecture models. The developer only has to select a template model, and to provide the desired interface to get the code generated. The package generation is made possible thanks to package templates, and we provide with the generator tool two templates for creating nodes either in C++ or Python. The user has also the possibility to design his own template, so that he can develop the one that best fits his needs and best practices. The package generator code is accessible on public repository hosting facilities.
Download

Paper Nr:	49
Title:	A Novel Approach for a Leg-based Stair-climbing Wheelchair based on Electrical Linear Actuators
Authors:	Emiliano Pereira, Hilario Gómez-Moreno, Cristina Alén-Cordero, Pedro Gil-Jiménez and Saturnino Maldonado-Bascón
Abstract:	The objective of this work is to develop a novel low-cost wheelchair capable to climb stairs (according to Spanish building regulation) and any obstacle similar to a step, to drive over uneven terrain such as cobblestones and adjust the height of the seat. The contribution presented in this work can be included into the leg-based stair-climbing mechanism classification. This work is a novel solution based on a previous patent, which proposed a wheelchair composed of nine linear actuators controlled by a pneumatic system. This novel approach proposes a mechanical modification in order to increase the flexibility of the mechanism, allowing the wheelchair to move up and down without changing the orientation, also guaranteeing the horizontal position of the user. In addition, the electric linear actuator presents some advantages with respect to the pneumatic system proposed in the previous design, being this wheelchair easier to be controlled. This works also presents the first prototype developed.
Download

Paper Nr:	50
Title:	Stereo Vision-based Autonomous Target Detection and Tracking on an Omnidirectional Mobile Robot
Authors:	Wei Luo, Zhefei Xiao, Henrik Ebel and Peter Eberhard
Abstract:	In this paper, a mobile robot equipped with an onboard computing unit and a stereo camera for autonomous target detection and tracking is introduced. This system can figure out an interesting target and track it robustly in real time. It is based on the ROS framework and can handle multi-resource information, such as RGB images, depth information, and IMU data. To balance the performance of the machine learning based object detection algorithm and the algorithm for object tracking, the Hamming distance and the intersection over union are selected as criteria. The performance of the system is verified in a hardware experiment in two typical scenarios.
Download

Paper Nr:	52
Title:	Theoretical and Experimental Modal Analysis of a 6 PUS PKM
Authors:	Francesco L. Mura, Hermes Giberti, Linda Pirovano and Marco Tarabini
Abstract:	In this article the modal analysis of a manipulator is presented and discussed from a theoretical and experimental perspective. The work focuses on both the simulation and the experimental stages of the modal analysis on six DOF parallel kinematics machine. In particular, the behavioural vibrational trend of the kinematics structure under analysis is presented within the entire workspace. Critical aspects of each test phase are highlighted as well as data post processing methods used. Finally, a map capable of summarizing the modal analysis results is shown.
Download

Paper Nr:	53
Title:	An Evaluation between Global Appearance Descriptors based on Analytic Methods and Deep Learning Techniques for Localization in Autonomous Mobile Robots
Authors:	Sergio Cebollada, Luis Payá, David Valiente, Xiaoyi Jiang and Oscar Reinoso
Abstract:	In this work, different global appearance descriptors are evaluated to carry out the localization task, which is a crucial skill for autonomous mobile robots. The unique information source used to solve this issue is an omnidirectional camera. Afterwards, the images captured are processed to obtain global appearance descriptors. The position of the robots is estimated by comparing the descriptors contained in the visual model and the descriptor calculated for the test image. The descriptors evaluated are based on (1) analytic methods (HOG and gist) and (2) deep learning techniques (auto-encoders and Convolutional Neural Networks). The localization is tested with a panoramic dataset which provides indoor environments under real operating conditions. The results show that deep learning based descriptors can be also an interesting solution to carry out visual localization tasks.
Download

Paper Nr:	54
Title:	Time Synchronisation of Low-cost Camera Images with IMU Data based on Similar Motion
Authors:	Peter Aerts and Eric Demeester
Abstract:	Clock synchronisation between sensors plays a key role in applications such as in autonomous robot navigation and mobile robot mapping. Such robots are often equipped with cameras for gathering visual information. In this work, we address the problem of synchronizing visual data collected from a low-cost 2D camera, with IMU (Inertial Measurement Unit) data. Both sensors are assumed to be attached to the same rigid body; hence, their motion is correlated. We present a motion based approach using a particle filter to estimate the clock parameters of the camera with the IMU clock as a reference. We apply the Lucas-Kanade optical flow method to calculate the movements of the camera in its horizontal plane corresponding to its recorded images. These movements are correlated to the motion registered by the IMU. This match allows a particle filter to determine the camera clock parameters in the IMU’s time frame and are used to calculate the timestamps of the images. We presume that only the IMU sensor provides timestamp data generated from its internal clock. Our experiments show that given enough features are present within the images, this approach has the ability to provide the image timestamps within the IMU’s time frame.
Download

Paper Nr:	62
Title:	Integration of an Autonomous System with Human-in-the-Loop for Grasping an Unreachable Object in the Domestic Environment
Authors:	Jaeseok Kim, Raffaele Limosani and Filippo Cavallo
Abstract:	In recent years, autonomous robots have proven capable of solving tasks in complex environments. In particular, robot manipulations in activities of daily living (ADL) for service robots have been widely developed. However, manipulations of grasping an unreachable object in domestic environments still present difficulty. To perform those applications better, we developed an autonomous system with human-in-the-loop that combined the cognitive skills of a human operator with autonomous robot behaviors. In this work, we present techniques for integration the system for assistive mobile manipulation and new strategies to support users in the domestic environment. We demonstrate that the robot can grasp multiple objects with random size at known and unknown table heights. Specifically, we developed three strategies for manipulation. We also demonstrated these strategies using two intuitive interfaces, a visual interface in rviz and a voice user interface with speech recognition. Moreover, the robot can select strategies automatically in random scenarios, which make the robot intelligent and able to make decisions independently in the environment. We demonstrated that our robot shows the capabilities for employment in domestic environments to perform actual tasks.
Download

Paper Nr:	65
Title:	Small Radius Spheres in Output Space of Nonholonomic Systems
Authors:	Arkadiusz Mielczarek and Ignacy Duleba
Abstract:	In this paper small radius spheres of driftless nonholonomic systems in an output space are analyzed. The nonholonomic systems appear frequently in mobile robotics. An algorithm is provided to compute the spheres extensively using a directional optimization and spherical coordinates. Illustrating examples are provided for two two-input nonholonomic systems. Results presented in this paper are important in motion planning of nonholonomic systems with outputs as a ready-to-use receipt is given how to shift a point in an output space in a desired direction. In practice, an effective short-distance motion planner is required while planning a motion in a space polluted with obstacles.
Download

Paper Nr:	86
Title:	Geometric Adaptive Robust Sliding-mode Control on SO(3)
Authors:	Yulin Wang, Xiao Wang, Shengjing Tang and Jie Guo
Abstract:	This paper addresses the rigid body attitude tracking control on the manifold SO(3) . This modeling scheme can avoid the singularity and ambiguity associated with local parameterization representations such as Euler angles and quaternion. A robust and almost global asymptotic stability control system is designed considering the parameters uncertainty and external interference. Based on the coordinate-free geodesic attitude error scalar function with its deduced attitude and velocity error vectors, a geometric asymptotic convergent sliding-mode surface is designed firstly. Then, a geometric sliding-mode controller is introduced to enhance the robustness of the system for the low-amplitude fast-time-varying disturbances. Moreover, in order to attenuate the effect of the parameters uncertainty and slow-time-varying disturbance, two adaptive functions are employed to obtain the feedforward compensation. Comparison studies and simulation results show that the proposed controller is more practical with a high accuracy, strong robustness, less chattering and simple structure.
Download

Paper Nr:	92
Title:	Technology of Developing the Software for Robots Vision Systems
Authors:	S. M. Sokolov, A. A. Boguslavsky and N. D. Beklemichev
Abstract:	The article describes the technology of developing the software for real-time vision systems. The article shows the position of this technology in the existing software tools. This technology is based on a unified software framework. This framework is an application model that implements the input and processing of the real time visual data. The framework structure provides prompt reprocessing for use in specific application tasks and is focused on the real time visual data processing. The article provides examples of vision systems based on the described framework. In addition, as the analysis shows, this framework can be jointly used with the ROS software through processing as a part of a separate ROS node.
Download

Paper Nr:	93
Title:	Nonlinear Output Feedback for Autonomous U-turn Maneuvers of a Robot in Orchard Headlands
Authors:	E. L. Flécher, A. Durand-Petiteville, F. Gouaisbaut, V. Cadenat, T. Sentenac and S. Vougioukas
Abstract:	This paper is devoted to the navigation of a robot in orchard headlands using embedded sensors such as lasers, Lidars or cameras. The main idea is to consider a differential robot model directly in polar coordinates and not in Cartesian coordinates which makes it possible to obtain simpler expressions of the outputs. Then two nonlinear output state feedback controllers are proposed to track two shapes based on spirals allowing to go from one row of fruit trees to another. These controllers are based on an input to output linearization and proved to be very efficient on simulations.
Download

Paper Nr:	103
Title:	Human-aware Robot Navigation in Logistics Warehouses
Authors:	Mourad A. Kenk, M. Hassaballah and Jean-François Brethé
Abstract:	Industrial and mobile robots demand reliable and safe navigation capabilities to operate in human populated environments such as advanced manufacturing industries and logistics warehouses. Currently mobile robot platforms can navigate through their environment avoiding coworkers in the shared workspace, considering them as static or dynamic obstacles. This strategy is efficient for safety, strictly speaking, but is not sufficient to provide humans integrity and comfortable working conditions. To this end, this paper proposes a human-aware navigation framework for comfortable, reliable and safely navigation designed to run in real-time on a mobile robot platform in logistics warehouses. This is accomplished by estimating human localization using RGB-D detector, then generating a virtual circular obstacle enclosing human pose. This virtual obstacle is then fused with the 2D laser range scan and used in ROS navigation stack local costmap for human-aware navigation. This strategy guarantees a different approach distance to obstacles depending on the human or non-human nature of the obstacle. Hence the mobile robot can approach closely to pallet to pick up objects while maintaining an integrity distance to humans. The reliability of the proposed framework is demonstrated in a workbench of experiments using simulated mobile robot navigation in logistics warehouses environment.
Download

Paper Nr:	104
Title:	Development and Implementation of Grasp Algorithm for Humanoid Robot AR-601M
Authors:	Kamil Khusnutdinov, Artur Sagitov, Ayrat Yakupov, Roman Meshcheryakov, Kuo-Hsien Hsia, Edgar A. Martinez-Garcia and Evgeni Magid
Abstract:	In robot manipulator control, grasping different types of objects is an important task, but despite being a subject of many studies, there is still no universal approach. A humanoid robot arm end-effector has a significantly more complicated structure than the one of an industrial manipulator. It complicates a process of object grasping, but could possibly make it more robust and stable. A success of grasping strongly depends on a method of determining an object shape and a manipulator grasping procedure. Combining these factors turns object grasping by a humanoid into an interesting and versatile control problem. This paper presents a grasping algorithm for AR-601M humanoid arm with mimic joints in the hand that utilizes the simplicity of an antipodal grasp and satisfies force closure condition. The algorithm was tested in Gazebo simulation with sample objects that were modeled after selected household items.
Download

Paper Nr:	114
Title:	An Improved APFM for Autonomous Navigation and Obstacle Avoidance of USVs
Authors:	Xiaohui Zhu, Yong Yue, Hao Ding, Shunda Wu, MingSheng Li and Yawei Hu
Abstract:	Unmanned surface vehicles (USVs) are getting more and more attention in recent years. Autonomous navigation and obstacle avoidance is one of the most important functions for USVs. In this paper, we proposed an improved angle potential field method (APFM) for USVs. A reversed obstacle avoidance algorithm was proposed to control the steering of USVs in tight spaces. In addition, a multi-position navigation route planning was also achieved. Simulation results in MATLAB show that the improved APFM can guide the USV to autonomously navigate and avoid obstacles around the USV during navigation. We applied the algorithm to a real USV, which is designed for water quality monitoring and tested in a real river system. Experimental results show that the improved APFM can successfully guide the USV to navigate based on the predefined navigation route while detecting both static and dynamic obstacles and avoiding collisions.
Download

Paper Nr:	119
Title:	A Modular Underactuated Gripper with Force Control System
Authors:	A. Margun, D. Bazylev, K. Zimenko and A. Kremlev
Abstract:	A design of an underactuated electromechanical gripper with force control algorithm is presented in this paper. The key feature of the gripper is the ability to grasp fragile objects and objects of a complex shape. Such advantages are due to the usage of elastic joints and force sensitive resistors embedded in modules of gripper’s fingers. Also low cost and mass of the presented device makes its application rational for a larger number of robotic systems. Proposed force control system is based on PI control and passification approaches that provide tuning simplicity and good performance in the case of unknown environments. Experimental results show the efficiency of proposed solution.
Download

Paper Nr:	123
Title:	Design, Estimation of Model Parameters, and Dynamical Study of a Hybrid Aerial-underwater Robot: Acutus
Authors:	Ridhi Puppala, Nikhil Sivadasan, Abhijeet Vyas, Akshay Molawade, Thiyagarajan Ranganathan and Asokan Thondiyath
Abstract:	Design of multi-domain vehicles has been a focus in robotics research in the recent past. The objective behind developing such hybrid vehicle/robot is to combine the capabilities of systems operating in various domains. They can be of great use in numerous applications, as it maximizes the reach in multiple operation environments, especially in various challenging sectors to reduce risk to the human lives. This paper presents the design of multi-domain vehicle: a hybrid aerial-underwater robot, Acutus. Dynamic modelling of Acutus is one of the vital steps in the design process. The parameters involved in the model such as the hydrodynamic drag and added mass are critical in determining the accuracy of the model. Mathematical modelling and estimation of system parameters for Acutus are presented. The dynamics of the system, both in aerial and underwater domains, are initially studied individually for different possible sets of inputs. Later, simulation studies are carried out for transition between aerial and underwater domains. Preliminary mechatronic design and the experimental setup details are also presented.
Download

Paper Nr:	142
Title:	Multiple DOF Platform with Multiple Air Jets
Authors:	Shinya Kotani, Nobukado Abe, Satoshi Iwaki, Tetsushi Ikeda and Takeshi Takaki
Abstract:	We have been studying noncontact object manipulation technology in which a single ball-shaped object is floated and controlled for its 3D position with multiple air jets driven by a pan-tilt actuator. In this paper, we try to control position and orientation of an arbitrary shaped object. Here an arbitrary object is connected with a triangle platform which is composed of three spheres linked with thin wires. Each sphere is spatially controlled by an air jet unit which consists of an air jet on a pan-tilt actuator. Kinematics of the air jet platform as a parallel link mechanism is calculated and a control method for the air jet platform is proposed.
Download

Paper Nr:	149
Title:	Development of an Experimental Strawberry Harvesting Robotic System
Authors:	Dimitrios S. Klaoudatos, Vassilis C. Moulianitis and N. A. Aspragathos
Abstract:	This paper presents the development of an integrated strawberry harvesting robotic system tested in lab conditions in order to contribute to the automation of strawberry harvesting. The developed system consists of three main subsystems; the vision system, the manipulator and the gripper. The procedure for the strawberry identification and localization based on vision is presented in detail. The performance of the robotic system is assessed by the results of experiments that take place in the lab and they are related to the recognition of occluded strawberries, the check of the strawberries for possible bruises after the grasping and the accuracy of detection of the strawberries’ location. The results show that the developed vision algorithm recognizes correctly every single strawberry and has high accuracy in recognizing occluded strawberries in which the largest part of each of them is visible. A small localization error results in a correct grasp and cut without causing damage to the fruit.
Download

Paper Nr:	153
Title:	Point-cloud Mapping using Lidar Mounted on Two-wheeled Vehicle based on NDT Scan Matching
Authors:	Kohei Tokorodani, Masafumi Hashimoto, Yusuke Aihara and Kazuhiko Takahashi
Abstract:	This paper presents a method for generating a 3D point-cloud map using multilayer lidar mounted on two-wheeled vehicle. The vehicle identifies its own 3D pose (position and attitude angle) in a lidar-scan period using the normal distributions transform (NDT) scan-matching method. The vehicle’s pose is updated in a period shorter than the lidar-scan period using its attitude angle and angular velocity measured by an inertial measurement unit (IMU). The pose estimation is based on the extended Kalman filter (EKF) under the assumption that the vehicle moves at nearly constant translational and angular velocities. The vehicle’s pose is further estimated in a period shorter than measurement period of the IMU using a linear interpolation method. The estimated poses of the vehicle are applied to distortion correction of lidar-scan data, and a point-cloud map is generated based on the corrected lidar-scan data. Experimental results of mapping a road environment using a 32-layer lidar mounted on a bicycle show the efficancy of the proposed method in comparison with conventional methods of distortion correction of lidar-scan data.
Download

Paper Nr:	157
Title:	Moving-object Tracking with Lidar Mounted on Two-wheeled Vehicle
Authors:	Shotaro Muro, Yohei Matsui, Masafumi Hashimoto and Kazuhiko Takahashi
Abstract:	This paper presents a tracking (estimating position, velocity and size) of moving objects, such as cars, two-wheeled vehicles, and pedestrians, using a multilayer lidar mounted on a two-wheeled vehicle. The vehicle obtains its own pose (position and attitude angle) by on-board global navigation satellite system/inertial navigation system (GNSS/INS) unit and corrects the distortion in the lidar-scan data by interpolating the pose information. The corrected lidar-scan data is mapped onto 3D voxel map represented in the world coordinate frame. Subsequently, the vehicle extracts the interested lidar-scan data from the current lidar-scan data using the normal distributions transform (NDT) scan matching based map-subtraction method. The extracted scan data are mapped onto an elevation map, and moving objects are detected based on an occupancy grid method. Finally, detected moving objects are tracked based on the Bayesian Filter. Experimental results show the performance of the proposed method.
Download

Paper Nr:	162
Title:	Development of Flow Rate Feedback Control in Tilting-ladle-type Pouring Robot with Direct Manipulation of Pouring Flow Rate
Authors:	Yuta Sueki and Yoshiyuki Noda
Abstract:	This paper describes the advanced control technology for the tilting-ladle-type pouring robots in the casting industry. In the pouring process in which the molten metal is poured into the pouring basin of the mold by tilting the ladle, it is difficult to pour the molten metal as desired pouring flow rate by the operator. Because the pouring flow rate is manipulated indirectly by manipulating the ladle’s angle. In order to solve this problem, in previous studies, we developed the direct manipulation system of the pouring flow rate in the pouring robots. However, the error between the desired and the actual pouring flow rate can be caused by the disturbances in the pouring condition. Therefore, in this study, we develop the pouring flow rate feedback control for improving the tracking performance. In this approach, the pouring flow rate can be estimated by using the extended Kalman filter, and the feedback controller can be constructed by the gain-scheduled PID control based on the estimated flow rate. The developed system is applied to the laboratory-type pouring robot. According to the experiments, the operator can manipulate the pouring flow rate as desired, even in the pouring condition with the disturbance.
Download

Paper Nr:	163
Title:	A Testing-environment for a Mobile Collaborative Stereo Configuration with a Dynamic Baseline
Authors:	Andreas Sutorma, Matthias Domnik and Jörg Thiem
Abstract:	This contribution deals with the construction of a testing-environment for the development of a camera based collaborative stereo configuration with a dynamic baseline. The use of a variable baseline for the stereo configuration allows to perform a more accurate depth calculation of the environment. For the development of such a collaborative stereo configuration it’s necessary to compare the results with ground-truth data. A VICON systems is a very capable solution for UAV and Robotic studies because of the high accuracy and low latency. This external localization system is intended to determine the dynamic stereo baseline at the first step of development. At a later progress this task will be taken over by another calibrated stereo camera that belongs to the mobile collaborative stereo configuration.
Download

Paper Nr:	176
Title:	Miniature Autonomy as One Important Testing Means in the Development of Machine Learning Methods for Autonomous Driving: How ML-based Autonomous Driving could be Realized on a 1:87 Scale
Authors:	Tim Tiedemann, Jonas Fuhrmann, Sebastian Paulsen, Thorben Schnirpel, Nils Schönherr, Bettina Buth and Stephan Pareigis
Abstract:	In the current state of autonomous driving machine learning methods are dominating, especially for the environment recognition. For such solutions, the reliability and the robustness is a critical question. A “miniature autonomy” with model vehicles at a small scale could be beneficial for different reasons. Examples are (1) the testability of dangerous and close-to-crash edge cases, (2) the possibility to test potentially dangerous concepts as end-to-end learning or combined inference and learning phases, (3) the need to optimize algorithms thoroughly, and (4) a potential reduction of test mile counts. Presented is the motivation for miniature autonomy and a discussion of testing of machine learning methods. Finally, two currently set up platforms including one with an FPGA-based TPU for ML acceleration are described.
Download

Paper Nr:	181
Title:	A Supervised Autonomous Approach for Robot Intervention with Children with Autism Spectrum Disorder
Authors:	Vinícius Silva, Sandra Queirós, Filomena Soares, João S. Esteves and Demétrio Matos
Abstract:	Technological solutions such as social robots and Objects based on Playware Technology (OPT) have been used in context of intervention with children with Autism Spectrum Disorder (ASD). Very often in these systems, the social robot is being fully controlled using the Wizard of Woz (WoZ) method. Although reliable, this method increases the cognitive workload on the human operator. They have to pay attention to the child and ensure that the robot is responding correctly to the child’s actions. In order to mitigate this, recently, researchers have been proposing the introduction of some autonomy in these systems. Following this trend, the present work targets a supervised behavioural system architecture using a novel hybrid approach with a humanoid robot and OPT to allow the detection of the child behaviour and consequently adapt the robot to the child’s action, enabling a more natural interaction. The system was designed for emotion recognition activities with children with ASD. Additionally, this paper provides an overview of the experimental design where the interventions will be carried out in school environments in a triadic setup (childrobot-researcher/therapist).
Download

Paper Nr:	184
Title:	Active Lower Limb Orthosis with One Degree of Freedom for Paraplegia
Authors:	Takuhiro Sunada, Goro Obinata and Yanling Pei
Abstract:	This paper describes a new design of active lower limb orthosis which is called as oneDHALO (one-actuator Drive Hip and Ankle Linked Orthosis). The oneDHALO has a linking mechanism which connects both ankle joints with a medial hip joint and an actuator which drives the rotation angle. The joints linkage mechanism keeps feet always in parallel with the floor to avoid stumbling, and assists swinging of the leg. One servo motor has been introduced to assist and control the movement constrained by the mechanism. To match the active movement to walking phase, optical sensors have been introduced at the soles for detecting the distance between the feet and floor. The control device which consists of internal communication system, sensor interfaces and a single board computer (Raspberry Pi) is designed for all in one with the mechanical part of the orthosis. The system has achieved continuous walking based on the feedback signals from the sensors. This paper reveals the preliminary experimental results of the system to show the good points of the design.
Download

Paper Nr:	185
Title:	Computed Torque Control of an Aerial Manipulation System with a Quadrotor and a 2-DOF Robotic Arm
Authors:	Nebi Bulut, Ali E. Turgut and Kutluk B. Aríkan
Abstract:	This paper presents the control of an aerial manipulation system with a quadrotor and a 2-DOF robotic arm by using the computed torque control method. The kinematic and dynamic model of the system is obtained by modeling the quadrotor and the robotic arm as a unified system. Then, the equation of motion of the unified system is got in the form of a standard robot dynamics equation. For the trajectory control of the system, computed torque control is used. Gains of the controller are optimized by using nonlinear least squares method. The performance and stability of the control structure are tested with a simulation case study.
Download

Paper Nr:	187
Title:	Investigation of Non-circular Scanning Trajectories in Robot-based Industrial X-ray Computed Tomography of Multi-material Objects
Authors:	Peter Landstorfer, Gabriel Herl and Jochen Hiller
Abstract:	In this work the application of six-axis robots for robot-based industrial X-ray computed tomography (CT) imaging is investigated. In contrast to classical Cartesian manipulators with a turntable used in industrial cone-beam CT, robots offer increased flexibility regarding scanning trajectories. The increased flexibility with respect to scanning trajectories helps to gather highly informative content from alternative ray paths for a high-quality 3D reconstruction of the object to be scanned. Using numerical simulations we show that this additional informations increase the image quality of a CT scan of a multi-material measuring object, consisting of tantalum spheres and a carbon structure.
Download

Paper Nr:	188
Title:	Lean Human-Robot Interaction Design for the Material Supply Process
Authors:	Marco Bonini, Augusto Urru and Wolfgang Echelmeyer
Abstract:	Powered by e-commerce and vital in the manufacturing industry, intralogistics became an increasingly important and labour-intensive process. In highly standardized automation-friendly environments, such as the automotive sector, most of efficiently automatable intralogistics tasks have already been automated. Due to aging population in EU and ergonomic regulations, the urge to automate intralogistics tasks became consistent also where product and process standardization is lower. That is the case of the production line or cell material supply process, where an increasing number of product variants and individually customized products combined with the necessary ability of reacting to changes in market conditions led to smaller and more frequent replenishment to the points of use in the production plant and to the chaotic addition of production cells in shop floor layout. This led in turn to inevitable traffic growth with unforeseeable related delays and increased level of safety threats and accidents. In this paper, we use the structured approach of the Quality Interaction Function Deployment to analyse the process of supply of assembly lines, seeking the most efficient combination of automation and manual labour, satisfying all stakeholdersŕrequirements. Results are presented and discussed.
Download

Paper Nr:	189
Title:	The Efficient Distribution Method of Limited Wireless Communication Frequency Resources for the Multi-robot Teaming
Authors:	Heeseo Chae, Jae H. Ju and Jae H. Park
Abstract:	In the situation where various defense robot systems are developed and operated, wireless network is an indispensable element to remotely control unmanned robots. However, when each defense robot is operated on the basis of wireless communication, the available frequency resources per robot are limited. At this point, if multiple robot operations are increased and the number of robots participating in them increased exponentially, a serious shortage of available frequencies is expected. Therefore, we propose a dynamic allocation of frequency resources as the bottom-up type approach to overcome this problem. More specifically, we implemented a bandwidth allocation scheme according to the priority change of each end node. We also show the validity and efficiency of this method through the related experimental results.
Download

Paper Nr:	193
Title:	FPGA-based Embedded System Designed for the Deployment in the Compliant Robotic Leg CARL
Authors:	Steffen Schütz, Atabak Nejadfard, Max Reichardt and Karsten Berns
Abstract:	The embedded system that is distributed within a bipedal robot is a key component of such a highly interwoven mechatronic system. Generally, it has to handle two competing main tasks – executing the embedded closed-loop control of the actuators and handling the communication with the higher-level control system. As the restrictions on physical size and energy consumption limit its computational resources, the design of the embedded nodes poses a potential bottleneck for the performance of the overall system. Hence, the following presents an approach to mitigate the conflicting requirements by deploying FPGA-based embedded nodes. It is illustrated how the additional flexibility at the logic level is used to implement the closed-loop force and impedance control of a series elastic actuator. Furthermore, it is shown how the consequent hardware/software co-design enables the deployment of a full featured robotic framework. To validate the concept, the properties of the implementation are characterized.
Download

Paper Nr:	198
Title:	Vision-based Localization of a Wheeled Mobile Robot with a Stereo Camera on a Pan-tilt Unit
Authors:	A. Zdešar, G. Klančar and I. Škrjanc
Abstract:	This paper is about a vision-based localization of a wheeled mobile robot (WMR) in an environment that contains multiple artificial landmarks, which are sparsely scattered and at known locations. The WMR is equipped with an on-board stereo camera that can detect the positions and IDs of the landmarks in the stereo image pair. The stereo camera is mounted on a pan-tilt unit that enables rotation of the camera with respect to the mobile robot. The paper presents an approach for calibration of the stereo camera on a pan-tilt unit based on observation of the scene from different views. Calibrated model of the system and the noise model are then used in the extended Kalman filter that estimates the mobile robot pose based on wheel odometry and stereo camera measurements of the landmarks. We assume that the mobile robot drives on a flat surface. In order to enforce this constraint, we transform the localization problem to a two-dimensional space. A short analysis of system observability based on indistinguishable states is also given. The presented models and algorithms were verified and validated in simulation environment. In this paper we present a system for tracking of a single static object in the environment with a stereo camera on-board of a WMR that is moving.
Download

Paper Nr:	203
Title:	A Terminal Sliding Mode Control using EMG Signal: Application to an Exoskeleton-Upper Limb System
Authors:	Sana Bembli, Nahla K. Haddad and Safya Belghith
Abstract:	This paper presents a robust terminal sliding mode control using the EMG signal. The application deals with an exoskeleton-upper limb system, used for rehabilitation. The considered system is a robot with one degree of freedom controlling the flexion/ extension movement of the elbow. The different stages of the EMG signal extraction were presented. Then, a second order terminal sliding mode algorithm has been developed to control the exoskeleton-upper limb system. A Stability study is realized and a robustness analysis is done using Monte Carlo simulation in presence of parametric uncertainties. Simulation results are provided to prove performance and effectiveness of the second order terminal sliding mode algorithm when tracking the EMG signal extracted from the human arm.
Download

Paper Nr:	204
Title:	MSER-based Framework for Classification of Objects in Thermal Images
Authors:	Alia Aljasmi and Andrzej Śluzek
Abstract:	In this paper, the problem of multi-class object recognition in thermal images is discussed. An alternative model of thermal objects is investigated, where an object is represented by multiple shapes extracted by MSER detectors. The shapes are nested within the largest MSER outlining the object (which might be the actual outline of the object, the outline of its thermal footprint or the outline of its largest prominent fragment). We show, using a multi-class dataset of thermal images captured in indoor environments, that the proposed methodology is a feasible solution for various object classification problems in thermal imaging. In particular, no object-specific algorithms are needed, so that the method is applicable to most of typical applications of thermal cameras (subject to general limitations of data captured by thermal imaging devices). The presented work is considered a preliminary feasibility study exploring potentials an limits of thermal image classification in more sophisticated machine vision problems.
Download

Paper Nr:	4
Title:	Path Planning of a Mobile Robot in Grid Space using Boundary Node Method
Authors:	R. A. Saeed and Diego R. Recupero
Abstract:	This paper presents a new off-line path planning method for a mobile robot to generate an optimal or near-optimal collision-free path between starting and goal points in a given working environment with obstacles. In a new method called Boundary Node Method, the robot is simulated by nine-node quadrilateral element, the centroid node represents the robot’s location and it moves with eight-boundary nodes in the working environments. A robot is exploring an environment with the help of the node’s potential value at each location, where the potential value is calculated based on the proposed potential function. The proposed method is capable of generating the initial collision-free path for a mobile robot safely and quickly. Subsequently, an additional new method called Path Enhancement Method is used to find shortest path by reducing the overall initial path length. The simulation results indicate that this method can successfully generate an optimal or near-optimal collision-free path efficiently.
Download

Paper Nr:	6
Title:	Collision Detection for a Mobile Robot using Logistic Regression
Authors:	Felix Becker and Marc Ebner
Abstract:	Collisions cannot be entirely avoided during normal operation of an autonomous mobile robot. Therefore, mobile robots need to detect collisions and react appropriately when they happen. We investigate whether logistic regression on acceleration data can be used for collision detection. We have collected training data from an acceleration sensor during normal driving behavior of a small mobile robot. Collisions were manually marked by a human operator. Accelerations occurring in a direction opposite to the current direction of motion are more likely to be actual collisions. Hence, we combine accelerometer data and motor commands in the logistic regression model. The trained model was able to detect 13 out of 14 collisions on a separate test set with no false positives.
Download

Paper Nr:	11
Title:	Integration of Open Source Arduino with LabVIEW-based SCADA through OPC for Application in Industry 4.0 and Smart Grid Scenarios
Authors:	Isaías G. Pérez, A. José Calderón Godoy and Manuel C. Godoy
Abstract:	Modern innovative concepts around Digital Information and Communication Technologies (DICTs), like Industry 4.0, the Internet of Things or Smart Grids, are impacting the scientific and technological worlds and, hence, in control and automation arenas. These trends involve networked interconnection and continuous data flow between a number of hardware and software actors. In parallel, open source technology has gained increasing attention from last years, especially due to the widespread presence of the open source hardware Arduino microcontroller. Focusing on industrial advanced frameworks, Supervisory Control and Data Acquisition (SCADA) systems are required to exchange data with new smart devices, sensors and/or actuators. Arduino boards are commonly used as development platforms for such smart devices. Therefore, communication solutions must be designed towards the convergence of open source hardware and widely used traditional SCADA-devoted software. This paper presents a system that seamlessly integrates Arduino boards into a LabVIEW-based SCADA system through Ethernet connection. The open connectivity provided by the Open Platform Communications (OPC) protocol enables such integration. The proposed framework is a novelty in scientific literature. The development of the system is reported and initial results are provided to demonstrate the feasibility of the proposal.
Download

Paper Nr:	24
Title:	An Approach to Marker Detection in IR- and RGB-images for an Augmented Reality Marker
Authors:	Aaronkumar Ehambram, Patrick Hemme and Bernardo Wagner
Abstract:	We introduce an augmented reality marker based on ArUco markers (Garrido-Jurado et al., 2014) that can be detected in RGB- and IR-images by using retroreflective material. Due to active perception by IR-capable camera systems the negative impact of external disturbances like change of light conditions on the marker detection is minimized. By the parallel processing architecture of RGB- and IR-images redundancy stabilizes the detection. As different retroreflective materials influence the image quality depending on the camera system, we also examined different retroreflective materials and compared the performance of the Kinect V2 and the Intel RealSense D435 regarding the detection probability depending on the geometrical distance of the augmented reality marker to the camera.
Download

Paper Nr:	27
Title:	Adaptive Controller for Uncertain Multi-agent System Under Disturbances
Authors:	Sergey Vlasov, Alexey Margun, Aleksandra Kirsanova and Polina Vakhvianova
Abstract:	This research is devoted to solving the problem of adaptive control algorithm synthesis for a mobile robots that is part of a multi-agent system. Proposed approach consists of trajectory planner and inner agent controller. The case of the passway intersection by the group of mobile robots is considered. Trajectory planner is based on intersection management approach. Adaptive consecutive compensator used for agent controller synthesis. Proposed approach provides control scheme which doesn’t depend on plant parameters. A group of mobile robots is built for experimental evaluation of proposed approach. Obtained results confirm effectiveness of the developed algorithms.
Download

Paper Nr:	29
Title:	Survey about the Utilization of Open Source Arduino for Control and Measurement Systems in Advanced Scenarios. Application to Smart Micro-Grid and Its Digital Replica
Authors:	Isaías G. Pérez, A. José Calderón Godoy, Manuel C. Godoy and J. G. González
Abstract:	The advantages of open source technology have led to their ever-growing utilization in advanced scenarios like the Industry 4.0, the Industrial Cyber-Physical Systems (ICPSs) and Smart Grids, among others. Concerning open source hardware, the platform Arduino receives great attention from academicians, hobbyists and even industrial practitioners. This paper aims at providing a panoramic overview of recent scientific literature reporting the use of Arduino in such challenging scenarios, proving its validity for control and measurement purposes. In addition, the application of such device as part of the equipment to monitor the operation and development of a Smart Micro-Grid and its digital replica is expounded.
Download

Paper Nr:	34
Title:	Smoothing and Time Parametrization of Motion Trajectories for Industrial Machining and Motion Control
Authors:	Květoslav Belda
Abstract:	The paper deals with path smoothing and time parametrization procedures intended for motion control of industrial machine tools and robots. Path smoothing, considered in this paper, is based on the application of Bézier curves. A possible straightforward solution ensuring compliance with given admissible positional tolerances is introduced. Consequent time parametrization considered here employs arc length and specific construction of acceleration polynomials. It describes the motion along the obtained smoothed curve geometry. It is given by timing the arc length, thus the construction of the feed rate profile. The key parts of the time parametrization comprise: computation of path length; time parametrization with respect to arc length; and decomposition to the individual Cartesian components describing individual curve coordinates. The theoretical results are presented by representative examples in 2D and 3D spaces.
Download

Paper Nr:	38
Title:	Reliability Analysis of the Kalman Filter for INS/GPS Integrated Navigation System Applied to Train
Authors:	Seong Y. Cho, Chang H. Kang and Kyung H. Shin
Abstract:	This paper aims to analyse the navigation performance that can be provided by the navigation system when applying the INS/GPS integrated navigation system to the train. The performance of the Kalman filter integrating INS and GPS can be summarized by the integrity of the measurement and the observability of the filter. Assuming the integrity of the GPS information used as a measurement is always satisfied, the performance of the filter can eventually be analysed by the observability. The observability of the filter depends on the dynamic trajectory of the train. Because the train has a non-holonomic constraint and one-dimensional motion, the filter design and the performance analysis are carried out considering this. We analyse the observability of the filter through simulation and explain the limit of the filter and the flaw of the observability. We also analyse the reliability of the navigation system and present additional research directions.
Download

Paper Nr:	46
Title:	Disturbance Observer for Path-following Control of Autonomous Agricultural Vehicles
Authors:	T. Hiramatsu, M. Pencelli, S. Morita, M. Niccolini, M. Ragaglia and A. Argiolas
Abstract:	This paper proposes a disturbance observer to be integrated inside a path-following controller in order to improve motion accuracy of an autonomous driving tractor. During operation, the tractor undergoes the effects of external forces due to either the action of the implement or the inclination of the ground. In such conditions, it is difficult to work precisely along a pre-determined path. By considering external forces as disturbances, it is possible to design a disturbance observer that estimates the steering angle on the basis of yaw-rate and lateral velocity. The proposed approach has been tested in a simulation environment.
Download

Paper Nr:	60
Title:	Quasi-serial Manipulator for Advanced Manufacturing Systems
Authors:	Bryan Kelly, J. Padayachee and G. Bright
Abstract:	Industrial automation has revolutionised manufacturing and the manufacturing environment. Advanced manufacturing requires a variety of different robotic manipulators for industrial applications, each with their defining characteristics. This research paper describes the differences between current industrial manipulators; it then proposes an open chain hybrid kinematic platform, consisting of closed loop parallelograms. The application of such a hybrid mechanism is apparent with material handling operations such as providing solutions for palletizing. A quasi-serial architecture was selected and its corresponding components were 3D printed. The forward kinematic equations were derived via a geometric approach. The outputs of these kinematic equations are then validated against empirical results obtained through an equivalent SolidWorks model of the robot.
Download

Paper Nr:	79
Title:	Progression of Human Hand Trajectory Variabilities during a Pick-and-Place Task
Authors:	Kolja Kühnlenz, Sergej Hermann, Kevin Kalb, Lucas Marschollek and Barbara Kühnlenz
Abstract:	This paper investigates the progression of human hand trajectory variabilities during a pick-and-place task. A user study is conducted and human hand positions are tracked optically. Standard deviations of human hand positions over all trajectories within a trial are computed point-wise orthogonally to the direct path between start and goal positions. Statistical tests reveal a decrease of standard deviations from hand start to goal positions. Moreover, stronger variations of standard deviations are noted in during the center part of the trajectories. Contrary to expectations, a longitudinal study design does not reveal learning effects in terms of reduction of trajectory variabilities. The results suggest, that uncertainties of human hand positions increase with the distance to a goal location and could constitute a larger risk for collisions within a cooperative human-robot pick-and-place scenario, e.g. assembly.
Download

Paper Nr:	88
Title:	Control of an Industrial Dual-arm Robot in a Narrow Space where Human Workers are Familiar with
Authors:	Taeyong Choi, Hyunmin Do, Donil Park and Jinho Kyungk
Abstract:	The industrial dual-arm robot is being developed. The developed industrial dual-arm robot aim to work with human workers or to work instead of human workers. Redundancy by high degree of freedom caused by arm and waist make robot movement difficult in the narrow space for human workers. Robot arms would take unexpected posture without proper redundant control method. In particular elbows can cause hazard situation by colliding with the environment or body of robot. Here novel method to control robot elbows is introduced. It shows good performance without loss of the position precision of end-effectors. Also it does not require high computing power, which make it useful for practical robot control. The proposed method is confirmed by the simulation.
Download

Paper Nr:	97
Title:	Towards Skills-based Easy Programming of Dual-arm Robot Applications
Authors:	Fan Dai
Abstract:	Programming dual-arm robotic applications requires good understanding of the tasks and the coordination between both arms must be well specified. This article analyses the synchronization modes required in dual-arm robot applications and describes a mechanism of programming these applications based on synchronizing the execution phases of robot skill functions for the two arms. Combined with a graphical user interface, it contributes to the ease of use of dual-arm robot systems.
Download

Paper Nr:	105
Title:	State Observers for Mechatronics Systems with Rigid and Flexible Drive Dynamics
Authors:	Alexandra-Iulia Szedlak-Stinean, Radu-Emil Precup and Radu-Codrut David
Abstract:	The mechatronics systems with rigid and flexible drive dynamics are nonlinear and complex processes. This paper proposes a controller with a novel structure, which is composed of three subsystems: a subsystem that provides the desired output and from the reference input a feed-forward signal, an observer and a feedback derived from the estimated states. This structure has the advantage that the response to reference signals can be decoupled from the response to disturbances. This paper also proposes observers based on predictive feedback, characterized by fast convergence and small sensitivity of the estimation to parameter variations. Design approaches for the controller and state observers are offered. The experimental setup considered in this paper, namely the Model 220 Industrial Plant Emulator (MIPE220), illustrates how the use of several control structures can be made accessible, easily understandable and increasingly attractive. The proposed design approaches are tested and validated in terms of conducting real-time experiments in terms of two experimental scenarios – step and staircase reference inputs – obtained for three specific values of the moment of inertia of the load disk.
Download

Paper Nr:	112
Title:	A Generalized Odometry for Implementation of Simultaneous Localization and Mapping for Mobile Robots
Authors:	Kethavath Raj Kumar
Abstract:	This paper proposes a novel method for calculation of generalized Odometry using velocities from Light Detection and Ranging (LiDAR) and Inertial Measurement Unit (IMU), discounting velocities from motor encoder values. Further, the estimated velocities are used for the calculation of Odometry using rigid body Newtonian equations. The generalized Odometry and laser scans are used for implementation of the particle filter Simultaneous Localization and Mapping (SLAM) algorithm. This method overcomes errors due to slippages in mobile robots. The outputs of SLAM maps are experimentally validated in both straight and curved trajectories with reference to ground truth maps. SLAM results obtained from the proposed method Odometry is better than the only LiDAR, IMU and Encoder Odometry in an indoor environment for autonomous navigation of mobile robots.
Download

Paper Nr:	116
Title:	Towards Total Coverage in Autonomous Exploration for UGV in 2.5D Dense Clutter Environment
Authors:	Evgeni Denisov, Artur Sagitov, Konstantin Yakovlev, Kuo-Lan Su, Mikhail Svinin and Evgeni Magid
Abstract:	Recent developments in 3D reconstruction systems enable to capture an environment in great detail. Several studies have provided algorithms that deal with a path-planning problem of total coverage of observable space in time-efficient manner. However, not much work was done in the area of globally optimal solutions in dense clutter environments. This paper presents a novel solution for autonomous exploration of a cluttered 2.5D environment using an unmanned ground mobile vehicle, where robot locomotion is limited to a 2D plane, while obstacles have a 3D shape. Our exploration algorithm increases coverage of 3D environment mapping comparatively to other currently available algorithms. The algorithm was implemented and tested in randomly generated dense clutter environments in MATLAB.
Download

Paper Nr:	164
Title:	A Novel Aerial Manipulation Design, Modelling and Control for Geometric CoM Compensation
Authors:	Kamel Bouzgou, Laredj Benchikh, Lydie Nouveliere, Yasmina Bestaoui and Zoubir Ahmed-Foitih
Abstract:	This paper presents the design and modelling of a new Aerial manipulating system, that resolve a displacement of centre of gravity of the whole system with a mechanical device. A prismatic joint between the multirotor and a robotic arm is introduced to make a centre of mass as close as to the geometric centre of the whole system. This paper details also the geometric and dynamic modelling of a coupled system with a Lagrange formalism and control law with a Closed Loop Inverse Kinematic Algorithm (CLIKA). This dynamic inverse control is validated in a Simulink environment showing the efficiency of our approach.
Download

Paper Nr:	177
Title:	Sitting Assistance that Considers User Posture Tolerance
Authors:	Daisuke Chugo, Masayu Koyama, Masahiro Yokota, Shohei Kawazoe, Satoshi Muramatsu, Sho Yokota, Hiroshi Hashimoto, Takahiro Katayama, Yasuhide Mizuta and Atsushi Koujina
Abstract:	This paper proposes a novel sitting assistance robot, which considers the posture tolerance of its user. The standing and sitting motion are different essentially because the standing is lifting motion against gravitational force and sitting is posture coordination to sitting position according to the gravity. Therefore, the robot should lead the patient’s posture within a stable range during sitting and the required performance is different from standing assistance. However, in previous studies, conventional assistive robots used the sitting motion which is “reverse” motion of standing. Furthermore, these robots helped patients by using a fixed motion reference pathway in spite of their original intention, and as the results, these robots failed to assist by confliction between their intended motion and reference path. Therefore, we propose a novel sitting assistance robot, which allows its user to move their body within a prescribed degree of posture tolerance during the process of moving from a standing to a sitting position. Our key findings cover two fundamental research topics. One is the investigation into posture tolerance during a sitting motion. The other topic is a novel assistance control algorithm that considers the investigated posture tolerance by combining position control and force control. A prototype assistive robot, based on the proposed idea was fabricated to help patients sitting down safely according to their original intention.
Download

Paper Nr:	199
Title:	Autonomous Gripping and Carrying of Polyhedral Shaped Object based on Plane Detection by a Quadruped Tracked Mobile Robot
Authors:	Toyomi Fujita and Nobuatsu Aimi
Abstract:	Recently, it is highly expected that robots work instead of human in a dangerous site such as disaster area. Sufficient working ability is required for such robots as well as moving ability. Thus, we present a method for autonomous gripping and carrying of a polyhedral shaped object by a mobile robot with multiple manipulation arms based on plane detection. Using this method, the robot can calculate appropriate observation positions for the detection of gripping planes and positions of the object. We apply the method to a quadruped tracked robot and verify its effectiveness in experiments for autonomous gripping and carrying of a box shaped object.
Download

Paper Nr:	212
Title:	Locomotion Mode Selection Plus (LMS+) Algorithm for Resource Efficient Outdoor Navigation
Authors:	Amir Sharif and Hubert Roth
Abstract:	Mobile robots that can fly in air and drive on ground may offer fast and energy efficient navigation. In this paper, a unique method has been proposed for optimal outdoor navigation of robots that can fly and drive. An offline dual mode path planning algorithm is developed and it is named as Locomotion Mode Selection Plus (LMS+) algorithm. It uses a two dimensional ground route from a web based geographic map server and makes a three dimensional resource optimised path, by considering dual mode locomotion. The results showed that the LMS+ algorithm makes a path that is optimised for travel time and energy consumption. The output path can be directly given to dual mode robots for resource optimised autonomous outdoor navigation.
Download

Area 4 - Signal Processing, Sensors, Systems Modelling and Control

Full Papers

Paper Nr:	3
Title:	Incremental Principal Component Analysis: Exact Implementation and Continuity Corrections
Authors:	Vittorio Lippi and Giacomo Ceccarelli
Abstract:	This paper describes some applications of an incremental implementation of the principal component analysis (PCA). The algorithm updates the transformation coefficients matrix on-line for each new sample, without the need to keep all the samples in memory. The algorithm is formally equivalent to the usual batch version, in the sense that given a sample set the transformation coefficients at the end of the process are the same. The implications of applying the PCA in real time are discussed with the help of data analysis examples. In particular we focus on the problem of the continuity of the PCs during an on-line analysis.
Download

Paper Nr:	17
Title:	Signal Estimation with Random Parameter Matrices and Time-correlated Measurement Noises
Authors:	R. Caballero-Águila, A. Hermoso-Carazo and J. Linares-Pérez
Abstract:	This paper is concerned with the least-squares linear estimation problem for a class of discrete-time networked systems whose measurements are perturbed by random parameter matrices and time-correlated additive noise, without requiring a full knowledge of the state-space model generating the signal process, but only information about its mean and covariance functions. Assuming that the measurement additive noise is the output of a known linear system driven by white noise, the time-differencing method is used to remove this time-correlated noise and recursive algorithms for the linear filtering and fixed-point smoothing estimators are obtained by an innovation approach. These estimators are optimal in the least-squares sense and, consequently, their accuracy is evaluated by the estimation error covariance matrices, for which recursive formulas are also deduced. The proposed algorithms are easily implementable, as it is shown in the computer simulation example, where they are applied to estimate a signal from measured outputs which, besides including time-correlated additive noise, are affected by the missing measurement phenomenon and multiplicative noise (random uncertainties that can be covered by the current model with random parameter matrices). The computer simulations also illustrate the behaviour of the filtering estimators for different values of the missing measurement probability.
Download

Paper Nr:	47
Title:	Experimental Implementation of Time-varying Input Shaping on UR Robots
Authors:	Dan Kielsholm Thomsen, Rune Søe-Knudsen, David Brandt and Xuping Zhang
Abstract:	Lightweight design leads to the unwanted vibration of industrial robot manipulators. Input Shaping (IS) has been proven to be an effective vibration suppression method. However, applying IS to suppress the vibration of industrial robots faces a challenging problem: time-varying dynamics. To address the time-varying dynamics of robot manipulators, this paper presents a novel and practical solution to vibration suppression based on Time-Varying Input Shaping Technology (TVIST). Our focus in this paper is to develop a practical implementation strategy that can be applied in discrete time. A Fractional Delay Finite Impulse Response filter is employed to design and implement TVIST. This solution makes TVIST more useful in practice because it can be combined with online and discrete-time trajectory generation. It can also be implemented in combination with position control using feed-forward velocity and torque. The performance of the new approach is validated through experimental implementation on a lightweight robot from Universal Robots A/S. Experimental results are analyzed to demonstrate significant vibration suppression and increased productivity of the robot with the proposed solution. The proposed method can be extended to the vibration suppression of other types of industrial robotic manipulators with serial links as well as other time-varying dynamic systems.
Download

Paper Nr:	72
Title:	Knowledge Transfer in a Pair of Uniformly Modelled Bayesian Filters
Authors:	Ladislav Jirsa, Lenka K. Pavelková and Anthony Quinn
Abstract:	The paper presents an optimal Bayesian transfer learning technique applied to a pair of linear state-space processes driven by uniform state and observation noise processes. Contrary to conventional geometric approaches to boundedness in filtering problems, a fully Bayesian solution is adopted. This provides an approximate uniform filtering distribution and associated data predictor by processing the involved bounds via a local uniform approximation. This Bayesian handling of boundedness provides the opportunity to achieve optimal Bayesian knowledge transfer between bounded-error filtering nodes. The paper reports excellent rejection of knowledge below threshold, and positive transfer above threshold. In particular, an informal variant achieves strong transfer in this latter regime, and the paper discusses the factors which may influence the strength of this transfer.
Download

Paper Nr:	84
Title:	VersaTL: Versatile Transfer Learning for IMU-based Activity Recognition using Convolutional Neural Networks
Authors:	Mubarak G. Abdu-Aguye and Walid Gomaa
Abstract:	The advent of Deep Learning has, together with massive gains in predictive accuracy, made it possible to reuse knowledge learnt from solving one problem in solving related problems. This is described as Transfer Learning, and has seen wide adoption especially in computer vision problems, where Convolutional Neural Networks have shown great flexibility and performance. On the other hand, transfer learning for sequences or timeseries data is typically made possible through the use of recurrent neural networks, which are difficult to train and prone to overfitting. In this work we present VersaTL, a novel approach to transfer learning for fixed and variable-length activity recognition timeseries data. We train a Convolutional Neural Network and use its convolutional filters as a feature extractor, then subsequently train a feedforward neural network as a classifier over the extracted features for other datasets. Our experiments on five different activity recognition datasets show the promise of this method, yielding results typically within 5% of trained-from-scratch networks while obtaining between a 24-52x reduction in the training time.
Download

Paper Nr:	91
Title:	Output Control and Disturbances Compensation using Modified Backstepping Algorithm
Authors:	D. E. Konovalov, S. A. Vrazhevsky, I. B. Furtat and A. S. Kremlev
Abstract:	The article deals with a problem of output control for linear systems under unknown mismatched disturbances. This algorithm is based on the modified backstepping method and the auxiliary loop method. The proposed control scheme is a robust approach intended to unknown mismatched disturbances estimation and compensation. Efficiency of the method is verified by computer modelling and practical approbation of the algorithm using a laboratory platform called "Twin Rotor MIMO System".
Download

Paper Nr:	94
Title:	Tsallis Divergence of Order 1/2 in System Identification Related Problems
Authors:	Kirill Chernyshov
Abstract:	The measure of divergence and the corresponding Hellinger-Tsallis mutual information have been introduced within the information-theoretic approach to system identification based on Tsallis divergence and Hellinger distance properties for a pair of probability distributions to be used in statistical linearization problems. The introduced measure in this case is used ambivalently: as mutual information, a measure of random vector dependence, — as a criterion of statistical linearization of multidimensional stochastic systems, and as a measure of divergence of probability distributions — as an anisotropic norm of input process used to quantify the correspondence between the observable data and the assumptions of the original problem statement as such.
Download

Paper Nr:	127
Title:	“ReLIC: Reduced Logic Inference for Composition” for Quantifier Elimination based Compositional Reasoning
Authors:	Hao Ren, Ratnesh Kumar and Matthew A. Clark
Abstract:	We present our work on the role and integration of quantifier elimination (QE) for compositional verification. In our approach, we derive in a single step, the strongest system property from the given component properties. This formalism is first developed for time-independent properties, and later extended to the case of time-dependent property composition. The extension requires additional work of replicating the given properties by shifting those along time so the entire time-horizon of interest is captured. We show that the time-horizon of a system property is bounded by the sum of the time-horizons of the component properties. The system initial condition can also be composed, which, alongside the strongest system property, are used to verify a postulated system property through induction. The above approaches are implemented in our prototype tool called ReLIC (Reduced Logic Inference for Composition) and demonstrated through several examples.
Download

Paper Nr:	146
Title:	Hybrid 6D Object Pose Estimation from the RGB Image
Authors:	Rafal Staszak and Dominik Belter
Abstract:	In this research, we focus on the 6D pose estimation of known objects from the RGB image. In contrast to state of the art methods, which are based on the end-to-end neural network training, we proposed a hybrid approach. We use separate deep neural networks to: detect the object on the image, estimate the center of the object, and estimate the translation and ”in-place” rotation of the object. Then, we use geometrical relations on the image and the camera model to recover the full 6D object pose. As a result, we avoid the direct estimation of the object orientation defined in SO3 using a neural network. We propose the 4D-NET neural network to estimate translation and ”in-place” rotation of the object. Finally, we show results on the images generated from the Pascal VOC and ShapeNet datasets.
Download

Paper Nr:	151
Title:	Analysis, Simulation and Control of a New Measles Epidemic Model
Authors:	Paolo Di Giamberardino and Daniela Iacoviello
Abstract:	In this paper the problem of modeling and controlling the measles epidemic spread is faced. A new model is proposed and analysed; besides the categories usually considered in measles modeling, the susceptible, the exposed, the infected, the removed and, less frequently, the quarantine individuals, two new categories are herein introduced: the immunosuppressed subjects, that can not be vaccinated, and the patients with an additional complication, not risky by itself but dangerous if caught togeter with the measles. These two novelties are taken into account in designing and scheduling suitably control actions such as vaccination, whenever possible, prevention, quarantine and treatment, when limited resources are available. An analysis of the model is developed and the optimal control strategies are compared with other not optimized actions. By using the Pontryagin principle, it is shown the prevailing role of the vaccination in guaranteeing the protection to immunosuppressed individuals, as well as the importance of a prompt response of the society when an epidemic spread occurs, such as the quarantine intervention.
Download

Short Papers

Paper Nr:	5
Title:	Phase Distribution in Probabilistic Movement Primitives, Representing Time Variability for the Recognition and Reproduction of Human Movements
Authors:	Vittorio Lippi and Raphael Deimel
Abstract:	Probabilistic Movement Primitives (ProMPs) are a widely used representation of movements for human-robot interaction. They also facilitate the factorization of temporal and spatial structure of movements. In this work we investigate a method to temporally align observations so that when learning ProMPs, information in the spatial structure of the observed motion is maximized while maintaining a smooth phase velocity. We apply the method on recordings of hand trajectories in a two-dimensional reaching task. A system for simultaneous recognition of movement and phase is proposed and performance of movement recognition and movement reproduction is discussed.
Download

Paper Nr:	8
Title:	Nonlinear System Identification using Neural Networks and Trajectory-based Optimization
Authors:	Hamid Khodabandehlou and M. S. Fadali
Abstract:	In this paper, we study the identification of two challenging benchmark problems using neural networks. Two different global optimization approaches are used to train a recurrent neural network to identify two challenging nonlinear models, the cascaded tanks and the Bouc-Wen system. The first approach, quotient gradient system (QGS), uses the trajectories of the nonlinear dynamical system to find the local minima of the optimization problem. The second approach, dynamical trajectory based methodology, uses two different nonlinear dynamical systems to find the connected components of the feasible region and then searches the regions for local minima of the optimization problem. Simulation results show that both approaches effectively identify the model of the cascade tanks and the Bouc-Wen model.
Download

Paper Nr:	10
Title:	Optimal Filtering Algorithm based on Covariance Information using a Sequential Fusion Approach
Authors:	R. Caballero-Águila, A. Hermoso-Carazo and J. Linares-Pérez
Abstract:	The least-squares linear filtering problem is addressed for discrete-time stochastic signals, whose evolution model is unknown and only the mean and covariance functions of the processes involved in the sensor measurement equations are available instead. The sensor measured outputs are perturbed by additive noise and different uncertainties, which are modelled in a unified way by random parameter matrices. Assuming that, at each sampling time, the noises from the different sensors are cross-correlated with each other, the sequential fusion architecture is adopted and the innovation technique is used to derive an easily implementable recursive filtering algorithm. A simulation example is included to verify the effectiveness of the proposed sequential fusion filter and analyze the influence of the sensor disturbances on the filter performance.
Download

Paper Nr:	14
Title:	PPG and EMG Based Emotion Recognition using Convolutional Neural Network
Authors:	Min S. Lee, Ye R. Cho, Yun K. Lee, Dong S. Pae, Myo T. Lim and Tae K. Kang
Abstract:	Emotion recognition is an essential part of human computer interaction and there are many sources for emotion recognition. In this study, physiological signals, especially electromyogram (EMG) and photoplethysmogram (PPG) are used to detect the emotion. To classify emotions in more detail, the existing method of modeling emotion which represents the emotion as valence and arousal is subdivided by four levels. Convolutional Neural network (CNN) is adopted for feature extraction and emotion classification. We measure the EMG and PPG signals from 30 subjects using selected 32 videos. Our method is evaluated by what we acquired from participants.
Download

Paper Nr:	15
Title:	Improved Relay Feedback Identification using Shifting Method
Authors:	M. Hofreiter
Abstract:	This paper presents a new method for estimation of a static gain and remaining parameters of a second order time delayed model by relay feedback identification. For this purpose, it uses a recently published method called shifting method which enables to estimate two points of frequency characteristic from a single relay feedback test. These two frequency response points are determined without any assumptions about a model transfer function and they can be used for fitting parameters of a process transfer function with various structures. For the first time the shifting method is used for a static gain estimation. This unique solution is even applicable under constant load disturbance. A great advantage for practical use is the comprehensibility and computational simplicity of the method. This identification method is primarily proposed for automatic tuning of controllers. The method is demonstrated on a simulated example and a laboratory apparatus “Air Aggregate”.
Download

Paper Nr:	33
Title:	Modeling of Passenger Demand using Mixture of Poisson Components
Authors:	Matej Petrouš, Evženie Suzdaleva and Ivan Nagy
Abstract:	The paper deals with the problem of modeling the passenger demand in the tram transportation network. The passenger demand on the individual tram stops is naturally influenced by the number of boarding and disembarking passengers, whose measuring is expensive and therefore they should be modeled and predicted. A mixture of Poisson components with the dynamic pointer estimated by recursive Bayesian estimation algorithms is used to describe the mentioned variables, while their prediction is solved with the help of the Poisson regression. The main contributions of the presented approach are: (i) the model of the number of boarding and disembarking passengers; (ii) the real-time data incorporation into the model; (iii) the recursive estimation algorithm with the normal approximation of the proximity function. The results of experiments with real data and the comparison with theoretical counterparts are demonstrated.
Download

Paper Nr:	48
Title:	Lines to Planes Registration
Authors:	Ales Jelinek and Adam Ligocki
Abstract:	This paper deals with the Line-Plane registration problem. First we introduce the matter of geometrical object fitting and show the specificity of the Line-Plane combination. Then the method is derived to fulfil all usual demands we put on a registration algorithm. Our algorithm works on any number of corresponding Line-Plane pairs higher than three, providing more accurate results and better convergence, as this number gets higher. Although the computation is non-linear by its nature, benefits of the least squares optimization were preserved. The algorithm is divided into a linear part dependant on the amount of input data and a non-linear part, which is not, keeping efficiency in case of large data sets. All important features were experimentally tested and proved to work.
Download

Paper Nr:	85
Title:	Robust Human Activity Recognition based on Deep Metric Learning
Authors:	Mubarak G. Abdu-Aguye and Walid Gomaa
Abstract:	In the domain of Activity Recognition, the proliferation of low-cost and sensor-enabled personal devices has led to significant heterogeneity in the data generated by users. Traditional approaches to this problem have previously relied on handcrafted features and template-matching methods, which have limited flexibility and performance with high variability. In this work we investigate the use of Deep Metric Learning in the domain of activity recognition. We use a deep Triplet Network to generate fixed-length descriptors from activity samples for purposes of classification. We carry out evaluation of our proposed method on five datasets from different sources with differing activities. We obtain classification accuracies of up to 96% in self-testing scenarios and up to 91% accuracy in cross-dataset testing without retraining. We also show that our method performs similarly to traditional Convolutional Neural Networks. The obtained results indicate the promise of this approach.
Download

Paper Nr:	87
Title:	Improved Dempster-Shafer Sensor Fusion using Distance Function and Evidence Weighted Penalty: Application in Object Detection
Authors:	Nazmuzzaman Khan and Sohel Anwar
Abstract:	Dempster-Shafer (DS) combination method can deal with the uncertainty and inconsistency of multi-sensor data fusion and widely used in data fusion, fault detection, pattern recognition, and supplier selection. The original DS theory has limitations such as its inability to handle conflicting data properly which can result into inaccuracy in the output of a multi-sensor data fusion process. To eliminate such limitations of the original DS theory, a novel method is proposed in this paper that uses distance function to measure the credibility of each sensor and uses weighted penalty of faulty sensor evidence to create maximum evidence for the correct detection. A detailed example for object detection with conflicting sensor input is presented which showcases all the steps of the proposed method. A numerical simulation is used to show that the proposed method effectively eliminates the limitations of original DS combination rule and offers an improvement over the current state-of-the-art models.
Download

Paper Nr:	95
Title:	Design of a Self-tuning Predictive PI Controller for Delay Systems based on the Augmented Output
Authors:	Yoichiro Ashida, Shin Wakitani and Toru Yamamoto
Abstract:	This paper proposes an online type control parameter tuning method for a predictive PI controller. Predictive PI controller is based on a PI controller with a Smith predictor, and it is effective for a controlled object with large dead-time. Control performance of the predictive PI controller strongly depends on control parameters. Recently, some data-driven controller tuning methods have been proposed. The methods directly calculate suitable parameters from one or some sets of operating data. In addition, almost controlled processes are time-variant. In this paper, a data-driven self-tuning predictive PI controller is proposed. The effectiveness of the proposed scheme is evaluated by a simulation example.
Download

Paper Nr:	106
Title:	On the Feasibility of On-body Roaming Models in Human Activity Recognition
Authors:	Mubarak G. Abdu-Aguye, Walid Gomaa, Yasushi Makihara and Yasushi Yagi
Abstract:	In the domain of human activity recognition, the primary goal is to determine the action a user was performing based on data collected through some sensor modalities. Common modalities adopted to this end include visual and Inertial Measurement Units (IMUs), with the latter taking precedence in recent times due to their unobtrusiveness, low cost and mobility. However, a secondary challenge arises in such sensor-based activity recognition. Difficulties in collecting and annotating training samples are significant and can hinder the performance of models trained on such limited data. As such, there is a need to explore techniques capable of tackling this problem in this domain. In this work, we explore the feasibility of reusing samples collected from different ”source” body locations in activity recognition at different ”target” body locations. This is achieved through the use of ”roaming” models based on recurrent neural networks. We investigate the predictive performance of the transferred samples relative to the performance from samples collected natively at the target body locations. Our results suggest that such roaming models can permit the reuse of cross-body samples without a significant loss in discriminative performance.
Download

Paper Nr:	110
Title:	Nonparametric System Identification Matlab Toolbox
Authors:	Grzegorz Mzyk
Abstract:	In the paper the first version of Nonparametric System Identification Matlab Toolbox is presented. It is based on theoretical results concerning nonparametric identification method, achieved for the last four decades. The library includes both standard (kernel based or orthogonal expansion based) nonparametric methods and recent algorithms including combined (parametric-nonparametric) algorithms. Hammerstein and Wiener models and their serial connections are considered. Nonparametric estimates, usually run as a preliminary steps, play supporting role in the main procedure of estimating system parameters by the least squares method. Multi-level (hybrid) structure of algorithms, i.e. combining both parametric and nonparametric approaches allows to decompose the problem of identification of interconnected complex system into simpler local subproblems. Moreover, asymptotic consistency of all estimates was formally proved, even under existence of random and correlated noise.
Download

Paper Nr:	113
Title:	Discrete-time Adaptive Regulation of Systems with Uncertain Upper-bounded Input Delay: A State Substitution Approach
Authors:	Khalid Abidi and Hang J. Soo
Abstract:	This paper proposes a discrete-time adaptive regulation approach for scalar linear time-invariant systems with unknown, constant input time delay that has a known upper-bound, without explicitly estimating the time delay. To cope with the unknown time delay, a state substitution is made that results in a delay free system that simplifies the control law design. In addition, the proposed approach does not require that the system have stable open-loop zeros. A stability analysis shows that the proposed regulator drives the system state to zero asymptotically and simulation results are shown to verify the approach.
Download

Paper Nr:	126
Title:	Electromyography Signal Analysis to Obtain Knee Joint Angular Position
Authors:	Edinson Porras, Lina Peñuela and Alexandra Velasco
Abstract:	Knee injuries are due to several causes and affect a large part of the population. In all of the cases, rehabilitation is required to recover the joint mobility and strength. In this context, the use of technology, especially the development of assistive devices may offer advantages to the patients, e.g. allow to perform correctly the exercises, adapt to the users’ needs and help to comply with the prescribed physical therapy. These devices may have specific requirements focused on not harming the patient. This is why control strategies are needed, and therefore feedback sensing is highly important. In this paper we present an algorithm to determine the knee joint angular position from surface Electromyography (EMG) measurements, using a curve fit from a polynomial adjustment method and a Locally Weighted Projection Regression (LWPR) method. We validate our approach, comparing the data obtained from the curve fitting with the measurements obtained with position sensors. In this way, results show that indeed we can explain the joint angular position with the EMG data taken in knee flexion-extension motion, applying a polynomial adjustment approach and the LWPR method.
Download

Paper Nr:	132
Title:	A Method for Static and Dynamic Interval Detection within the IMU Calibration Procedure
Authors:	Andrejs Zujevs, Valters Vecins and Aleksandrs Korsunovs
Abstract:	An Inertial Measuring Unit (IMU) is used for measuring linear accelerations and angular velocities in 3D/2D space. IMU devices are usually designed as micro-electro-mechanical systems (MEMS), which are produced in small form factor and are widely used in robotics, mobile phones and drones. Depending on the quality of the device, they can be divided into low-cost and high-cost IMUs. The main difference between them is the accuracy of measurements and IMUs mechanical alignment on the printed circuit board. The high-cost IMUs are well calibrated and have a relatively small error and noise level for different kinds of parameters. In contrast, the low-cost IMUs have a larger error component, where body frame axes are non-orthogonal for both the accelerometer and gyroscope due to weak factory calibration, high noise and high sensitivity dependence from the temperature, misalignment of body frame due to packaging and assembly processes. This paper provides a new method for the IMU static and dynamic interval detection within the IMU calibration procedure, which is designed by other authors for the case of IMU calibration without any external equipment. This procedure uses a sequence of alternating static and dynamic intervals for accelerometer calibration and then gyroscope calibration. The accuracy of the IMU calibration procedure depends strongly on how precisely static and dynamic intervals have been detected. Otherwise, the calibration results are unsuitable. The new method for static and dynamic interval detection provides more robust and less noisy results, requires a significantly smaller number of operations and is easy to implement. The paper provides comparative results for both methods and refers to the source code for the new method.
Download

Paper Nr:	140
Title:	Computation of Trajectory Sensitivities with Respect to Control and Implementation in PSAT
Authors:	Ramij R. Hossain and Ratnesh Kumar
Abstract:	Trajectory sensitivity based analysis is widely regarded as an important tool for real time protection scheme of power systems. Model Predictive Control (MPC) for voltage instability is one such protection scheme which computes a sequence of control actions depending upon the trajectory behaviour of the dynamics of the power systems. Thus, computation of trajectory sensitivities with respect to control input can be an integral part for designing a real-time protection scheme. In this context, it is important to note that for the state-of-the-art Power System Analysis Tool (PSAT)(Milano, 2005), (Milano et al., 2008), while it is relatively easy to compute the trajectory sensitivities with respect to any system variables, the computation of trajectory sensitivities with respect to control inputs is not explicitly supported. This paper presents a method to extend the functionality of PSAT to also compute the trajectory sensitivities with respect to control inputs, which ultimately forms the basis for real-time protection schemes such as MPC. The proposed method is validated using direct time-domain simulation results.
Download

Paper Nr:	141
Title:	On Dynamic Output Feedback H∞ Control for Positive Discrete-Time Delay Systems
Authors:	Baozhu Du
Abstract:	This paper is devoted to the H∞ control design of positive discrete-time systems with multiple delays. Novel bounded real lemma is presented first via linear matrix inequality technique, which reveals that H∞ norms of a discrete-time positive system with time delays both in dynamic and output equations are identical to that of the corresponding delay-free system. Necessary and sufficient conditions for positivity preserving H∞ stabilization via a dynamic output feedback control are established in the forms of matrix equalities, that guaranteeing the closed-loop system not only to be asymptotically stable and positive, but also to have a desired H∞ performance. The proposed results are extended to interval uncertain positive systems with time delay. Finally, an example is given to illustrate the effectiveness of the obtained design scheme.
Download

Paper Nr:	160
Title:	Force Display Control System using 2 DOF Admittance Control in Surgical Training Simulator with Chiseling Operation
Authors:	Kentaro Masuyama, Yoshiyuki Noda, Yasumi Ito, Yoshiyuki Kagiyama and Koichiro Ueki
Abstract:	This study contributes to developing the virtual surgical training simulator for chiseling operation. In surgical operations using the bone chisel, impact forces are applied to the bone by pounding the chisel with the mallet. To virtually represent this situation in the training simulator, the force display system with high stiffness and instant reaction to the impact force is needed. In order to realize this force display system, we constructed the force display device with the ball-screw mechanism for obtaining the high stiffness, and proposed the two degree-of-freedom (2 DOF) admittance control for reacting instantaneously in the previous study. In this study, the force display control system using 2 DOF admittance control is analyzed, and the feedforward and feedback controllers in 2 DOF admittance control are developed for improving the reaction of the force display device. The efficacy of the proposed control system is verified by creating a virtual experience to the chiseling manipulation of a hard object using the bone mallet. From the experimental results, it is confirmed that the movement, contact, chiseling and splitting sensations are displayed more accurately than the conventional approach.
Download

Paper Nr:	170
Title:	A Preliminary Study of Ankle Variable Hybrid Above-knee Prostheses
Authors:	Su-Hong Eom, Sun-Jong Na, Sang-Hyun Lee, Se-Hoon Park and Eung-Hyuk Lee
Abstract:	This study is a preliminary study to solve problems in gait imbalance at slope ways and low ramps with ankle variable hybrid above-knee prostheses. For the purpose of implementing ankle variable control, the stance phase in gait was determined as a step-by-step manner and the threshold values were derived through the decision tree learning method based on inertial sensor data in verifying the swing phase. It can be used to perform the ankle variable control. The control of the hybrid above-knee prosthesis was demonstrated by measuring butterfly diagrams on a low ramp for verifying the gait balance in the test ramp.
Download

Paper Nr:	179
Title:	Time-based Countermeasures for Relay Attacks on PKES Systems
Authors:	Yifan Xie, Hyung J. Kim, Sa Y. Chong and Taek L. Song
Abstract:	The development of passive keyless entry and start (PKES) systems in modern vehicles enables drivers to access and control their vehicles remotely using smart keys, which improves the driving conveniences. The PKES system verifies the smart key identity if the communication channel between the vehicle and the smart key is established. When the message in the communication channel is relayed by other devices, it can be manipulated by the attackers and the PKES systems become vulnerable. The distance bounding protocol, which estimates the physical proximity between the vehicle and the smart key, is one of the countermeasures against relay attacks. In this paper, the time-based distance bounding is studied. Since the effectiveness of distance bounding protocol relies heavily on the estimation accuracy, various time-based estimation algorithms are enumerated and compared in this paper.
Download

Paper Nr:	180
Title:	Neural Network Contour Error Prediction of a Bi-axial Linear Motor Positioning System
Authors:	Krystian Erwinski, Karol Kowalski and Marcin Paprocki
Abstract:	In the article a method of predicting contour error using artificial neural network for a bi-axial positioning system is presented. The machine consists of two linear stages with permanent magnet linear motors controlled by servo drives. The drives are controlled from a PC with real-time operating system via EtherCAT fieldbus. A randomly generated Non-Uniform Rational B-Spline (NURBS) trajectory is used to train offline a NARX-type artificial neural network for each axis. These networks allow prediction of following errors and contour errors of the motion trajectory. Experimental results are presented that validate the viability of the neural network based contour error prediction. The presented contour error predictor will be used in predictive control and velocity optimization algorithms of linear motor based CNC machines.
Download

Paper Nr:	194
Title:	MIMO Fuzzy Control Solutions for the Level Control of Vertical Two Tank Systems
Authors:	Claudia-Adina Bojan-Dragoş, Elena-Lorena Hedrea, Radu-Emil Precup, Alexandra-Iulia Szedlak-Stinean and Raul-Cristian Roman
Abstract:	The paper presents the design and validation of two control system (CS) structures for the level control of vertical two tank systems. The first CS structure consists of a Multi Input Multi Output Proportional Integral Fuzzy Controller with integration of controller input (MIMO–PI–FC–II) and the second CS structure consists of a Multi Input Multi Output Proportional Integral Fuzzy Controller with integration of controller output (MIMO–PI–FC–OI). The suggested CS structures are designed using the modulus optimum method and the modal equivalence principle. The experimental results validate the proposed control solutions. Finally a comparative analysis is also included.
Download

Paper Nr:	211
Title:	Low-cost Sonar based on the Echolocation
Authors:	Thiago Moreira, José Lima, Paulo Costa and Márcio Cunha
Abstract:	In the world of mobile robot navigation, the ultrasonic sensors stand out for presenting attractive features at an affordable cost. The main problem in the use of these devices lies in the difficulty of correctly interpreting the obtained data, which means that their efficiency is limited. This paper focuses on the improvement and implementation of a low cost location system based on ultrasonic sensors. Through the combination of mathematical techniques and signal processing it is possible to make the system more accurate and reliable. The developed system includes the data acquisition, the signal filtering, and the trigonometric methods to estimate the coordinates of a target and can be assembled in a mobile robot.
Download

Paper Nr:	2
Title:	Control of Uncertain Time Delay System with Astatism and Parametric and Periodic Uncertainties using SSV and Factorization for Two-Degree-of-Freedom-Controller
Authors:	Marek Dlapa
Abstract:	Application of the Robust Control Toolbox for Time Delay Systems with Parametric and Periodic Uncertainties Using SSV (Structured Singular Value) for the Matlab system to uncertain time delay system with astatism is performed. The D-K iteration and the algebraic approach implemented in the toolbox are applied to 2nd order system with astatism and uncertain time delay and two other parameters in the numerator and denominator of the plant transfer function. Multiplicative uncertainty is used for treating uncertain time delay, the parametric uncertainty is modelled using general interconnection for the systems with parametric uncertainty in numerator and denominator.
Download

Paper Nr:	16
Title:	A Reconfigure Modelling of Double Stator PMSM after Turn-to-Turn Short Circuit
Authors:	Li Hao, Emmanuel Schaeffer and Tang Tianhao
Abstract:	This article presents an original modelling of a high speed double stator permanent magnet synchronous machine (DSPMSM). When a turn-to-turn short-circuit fault occurs in the stator windings, the current flowing in the short-circuited turns can be much higher than the phase current. And the unbalance between the phases caused by the fault makes the phase voltage unmeasured. For overcoming this problem, a reconfiguration modelling method is proposed. The reconfiguration is a model which input line voltage rather phase voltage that can be measured correctly even if the machine is unbalanced. This advanced model is familiar with the classical d-q model. Therefore the traditional vector control algorithm is still available, the machine can be controlled by using the same signals (measured phase currents at the inverter level and DC bus voltage). A simulation of a DSPMSM variable speed drive shows the relevance of the model.
Download

Paper Nr:	55
Title:	Drive Chain Friction Characterization of a 6DOF Parallel Kinematics Robot
Authors:	Hermes Giberti, Francesco L. Mura, Ivan Raineri and Marco Tarabini
Abstract:	This paper describes a time-efficient method for friction characterization on a Robot drive chain, namely a Ball-screw transmission. The Method promotes practical application by being independent from external sensors and giving very precise and usable output model. A complete extimation procedure is described togheter with the results obtained on the real Machine.
Download

Paper Nr:	61
Title:	Fractional Controller for Thin Plate Surface Temperature Control
Authors:	Dan S. Necsulescu, Bilal A. Jarrah and Jurek Z. Sasiadek
Abstract:	Surface temperature control of a thin aluminium plate were investigated using closed loop control approach implemented using inverse problem. The one-dimensional model with periodic boundary condition was solved using the Laplace transform and both direct problem and inverse problem transfer functions were obtained. The resulting transfer functions were expanded using Zero-Pole expansion to obtain a finite order polynomial transfer function. Simulation results for closed loop control using fractional controllers (FOPIλ, FOPDμ, and FOPIDμ) were evaluated.
Download

Paper Nr:	63
Title:	A Multi-layer Ontology for Data Processing Techniques
Authors:	Man Tianxing, Nataly Zhukova, Nguyen Than, Alexander Nechaev and Sergey Lebedev
Abstract:	Currently, data processing technology is applied in various fields. But non-expert researchers are always confused about its diversity and complex processes. Especially due to the instability of real data, the preparation process for extracting information is lengthy. At the same time, different analysis algorithms are based on different mathematical models, so they are suitable for different situations. In the real data processing process, inappropriate data forms and algorithm selections always lead to unsatisfactory results. This paper proposes a multilayer description model of data processing algorithms and implements it based on ontology technology. The model provides a multi-layered structure including data pre-processing, data form conversion, and output model selection so that the user can obtain a complete data processing process from it. The extensibility and interpretability of ontology also provide a huge space for model improvement. The multilevel structure greatly reduces its complexity.
Download

Paper Nr:	115
Title:	Wavelet Analysis based Stability Conditions of a Prediction Model
Authors:	Ekaterina Sakrutina
Abstract:	Prediction models found a wide application in advanced control systems, intelligent systems of information decision support, play a significant role in any activity concerned with signal processing procedures, involving detecting failures of different technological processes. Methods based on the wavelet analysis are characterized by a unique ability of detailed frequency analysis in the time. The paper presents stability conditions of a prediction model, which are developed on the basis of the multi-scale wavelet transform, as well an example of the prediction model applied in the oil refining process.
Download

Paper Nr:	118
Title:	Design and Implementation of Smart Micro-Grid and Its Digital Replica: First Steps
Authors:	A. José Calderón Godoy and Isaías G. Pérez
Abstract:	It is evident the digital transformation that is spreading in more and more areas of science and technology in recent times, as demonstrated by scenarios such as Smart Grids, the Internet of Things, Cyber-Physical Systems or the Industry 4.0. This article outlines the first steps followed to develop a research project which aim is to bring this digitalization to the field of renewable energies and intelligent energy generation and distribution grids, the so-called Smart Grids (SG). The objective of this project is twofold. On the one hand, all the steps necessary to develop digital replicas of the devices that make up a Smart Micro-Grid will be covered. On the other hand, an automation and energy management system will be implemented over the micro-grid to optimize the operation of each of the systems that compose it, while guaranteeing the energy demand and maximizing the use of solar energy. Additionally, hydrogen is used as mid/long-term energy storage system (backup).
Download

Paper Nr:	125
Title:	Buck Converter Modeling in High Frequency using Several Transfer Function-based Approaches
Authors:	Imen Shiri, Sanda Lefteriu and Cécile Labarre
Abstract:	The recent development of large gap (GaN) components adapted to high frequency operation opens up interesting perspectives for the emergence of high power density static converters. However, the implementation of GaN components requires the development of new characterization, modeling and design methods adapted to these fast components. In this paper, we present three modeling techniques for a static converter in the frequency domain. They are all characterizing the input - output transfer function and they are: the average model, the generalized transfer function (GTF) and the modified nodal analysis technique (MNA). These models, already existing in the literature, are extended to account for the parasitic effects of the switching elements (diodes or transistors). In fact, parasitic elements associated with the different passive and active components are inherent in a power electronics structure. Their effects are negligible in low frequency but they are preponderant in high frequency. Simulation results performed for a Buck converter show that, while the GTF and the MNA are able to predict the resonances present at multiples of the switching frequency, the average model does not. In terms of the influence of the parasitic elements on the transfer function, the peak which is due to the output filter parameters is attenuated. Lastly, the experimental validation shows that, even with the introduction of the parasitic elements of the switching components, there are still discrepancies between the models and the data, so additional parasitics still need to be accounted for.
Download

Paper Nr:	131
Title:	Neural Networks Modelling of Aero-derivative Gas Turbine Engine: A Comparison Study
Authors:	Ibrahem A. Ibrahem, Ouassima Akhrif, Hany Moustapha and Martin Staniszewski
Abstract:	In this paper, the modelling of aero derivative gas turbine engine with six inputs and five outputs using two types of neural network is presented. Siemens three-spool dry low emission aero derivative gas turbine engine used for power generation (SGT-A65) was used as a case study in this paper. Data sets for training and validation were collected from a high fidelity transient simulation program. These data sets represent the engines operation above its idle status. Different neural network configurations were developed by using of a comprehensive computer code, which changes the neural networks parameters, namely, the number of neurons, the activation function and the training algorithm. Next, a comparative study was done among different neural models to find the most appropriate neural network structure in terms of computation time of neural network training operation and accuracy. The results show that on one hand, the dynamic neural network has a higher capability than the static neural network in representation of the engine dynamics. On the other hand however, it requires a much longer training time.
Download

Paper Nr:	161
Title:	A Study on the Activation of Femoral Prostheses: Focused on the Development of a Decision Tree based Gait Phase Identification Algorithm
Authors:	Sun-Jong Na, Jin-Woo Shin, Su-Hong Eom and Eung-Hyuk Lee
Abstract:	This paper aims to classify the phase of gait for passive transfemoral prostheses as a preliminary study for the development of a knee flexion angle control device in prosthetics by attaching it to the knee joint in order to produce a walk trajectory like a normal person, while walking on a flat. However, it is not possible to determine a gait stage according to the inflection point of a knee, since there are few angular changes in the knee joint in the form of a seat that will support the body. Thus, in previous studies, algorithms were developed to distinguish between three stages of the stance in the swing phase using a decision tree learning method. However, the decision-making tree is prone to overfitting. This can be a high level of accuracy for training data, but it is difficult to generalize when verification data or new data are entered. Therefore, in this paper, we want to develop an algorithm for preventing the overfitting step-by-step using two different methods.
Download

Paper Nr:	167
Title:	State Observability through Prior Knowledge: A Conceptional Paradigm in Inertial Sensing
Authors:	Tom L. Koller, Tim Laue and Udo Frese
Abstract:	Inertial Navigation Systems suffer from unbounded errors on the position and orientation estimate. Exteroceptive sensors may not always be available to correct the error. Applications in the literature overcome this problem by fusing IMU data with prior knowledge in an ad-hoc fashion. In different applications, various knowledge is available, which allows to correct the erroneous state estimate. In this position paper, we argue that the fusion of knowledge and inertial sensor data should be viewed as a paradigm and that the observability of systems with prior knowledge should be analysed theoretically. With a theoretical foundation, application design will be simplified and verifiable. We show methods to start the analysis and give a first proof with practical insight.
Download