Keynote Lectures

Abstract
(joint work with Peter Robinson, University of Queensland)

We describe a multi-threaded robotic agent architecture in which multiple compatible tasks, sharing one or more external robotic resources, can be executed concurrently without: starvation, interference or deadlock.  Each task progressively achieves sub-goals of the task goal. There is parallel use of disjoint sets of resources whenever possible.

The agents are programmed in two rule based languages: TeleoR and QuLog. The roots of TeleoR go back to the conditional action plans of the first cognitive robot, SRI’s Shakey. These lead to Nilsson’s Teleo-Reactive robotic agent language T-R. TeleoR is a major extension of T-R

QuLog is a flexibly typed multi-threaded logic+function+action rule language. Its declarative subset is used for encoding the agent’s dynamic beliefs and static knowledge. Its action rules are used for programming agent threads and inter-agent communication. The guards of TeleoR robotic action rules are QuLog queries to the agent’s dynamic beliefs using its knowledge rules.

Because of the structure and distinctive operation semantics of a TeleoR program, the agent will respond to help or hindrance without the need to re-plan a task behaviour. If helped it skips the actions it would normally do to achieve the task sub-goal achieved by the help. If hindered, it attempts to re-achieve the last sub-goal it had reached, or to achieve the task goal by another sub-goal route. This flexible behaviour makes TeleoR well suited to human/robot co-operative tasks.

We introduce the use of TeleoR and QuLog, and the multi-threaded agent architecture, with two robot control applications:

• A multi-tasking agent controlling two independent robotic arms in multiple construction tasks. Colleagues at UNSW Sydney have ported this to a Baxter robot, See https://www.doc.ic.ac.uk/~klc/20160127-LABCOT-HIx4.mp4
• Single task communicating agents each separately controlling a track following robot navigating through doorways that are exogenously opened and closed to a destination room. This is done without risk of collision and with continuous recompilation of the shortest path through doorways believed to be open. See https://www.doc.ic.ac.uk/~klc/pathFollowers.mp4
• In the second application communication is as important as perception. The agents re-compute 
• Their doorway route immediately they see or are informed by another agent that a doorway 
• They intended to use is closed. They keep one another informed re their room location and
• Path following intention, information used for avoidance behaviour. 

Abstract
It is quite common for the robotics community to work across disciplines, be it by pulling in various engineering competences or by linking to social sciences, including humanities, economy etc.: We just got used to combine actuators and sensors, hardware and software, real and virtual worlds in complex systems, and beyond engineering, we worked with other sciences to learn about their look on robotics as well, when the complex systems matured and visibly started to affect markets and people.

Today, the various aspects of Smart Production (or also Smart Energy, Smart Home, Smart X) pretty much ask for activating a similar, vertical integration of disciplines from engineering and beyond in order to analyze and develop smart, complex systems which combine actuators and sensors, hardware and software, real and virtual worlds. In robotics, we are thus actually sitting right in the middle of ongoing and upcoming developments in Smart X, and we have the advantage of being accustomed to the necessary mindset of connecting to a variety of competences.

High expectations were built up regarding robotics in this comfortable spearhead position. Of course, research is exactly that - research, operating at the fringes of conventional solutions and mostly dealing with problematic and open questions. Still, we should now also critically look after fulfilling some of these expectations, be it by transferring our examples from research to actual applications or by reassessing our tools and processes if they are sufficiently fit for supporting such transfers.

In this regard, at SDU Robotics, we aim for addressing this transfer gap by building up close cooperations with external partners and by linking our tools and processes to existing formats and standards. In my talk, I will show examples of this approach, our unique situation in Odense, Denmark, and how we conceive simulation and digital twins to pave the way to deliver tangible and robust results from our research.

Abstract
The state of the art of robotic manipulation is still rather far from the human dexterity in the execution of complex motions such as, for example, in dynamic manipulation tasks. Dynamic manipulation is considered as the most complex category of manipulation requiring ad-hoc controllers and specialized hardware. In case of non-prehensile manipulation or non-rigid objects, the task of dynamic manipulation becomes even more challenging. This reduces the opportunities for wide adoption of robots within human co-habited environments.
This talk presents the results achieved within the RoDyMan project related to planning and control strategies for robotic non-prehensile manipulation. The project aims at advancing the state of the art of non-prehensile dynamic manipulation of rigid and deformable objects to further enhance the possibility of employing robots in anthropic environments. The final demonstrator of the RoDyMan project will be an autonomous pizza maker. The lessons learned so far are highlighted to pave the way towards future research directions and critical discussion.