Special Session
Special Session on
Hybrid Intelligence: Integrating Physics-Based Principles with Data-Driven AI -
HybAI
2026
26 - 28 October, 2026 - Angers, France
Within the 23rd International Conference on Informatics in Control, Automation and Robotics - ICINCO 2026
CO-CHAIRS
|
Vittorio Lippi
Calejo Hybrid Intelligence AB
Germany
|
|
|
|
Brief Bio
Dr. Vittorio Lippi holds a PhD in Robotics from the Scuola Superiore Sant'Anna in Pisa, Italy, a BSc in Computer Engineering, and an MSc in Industrial Automation from the Università di Pisa. He currently serves as an Artificial Intelligence Officer at Calejo Hybrid Intelligence AB, where his work focuses on integrating machine learning, control theory, and simulation for complex real-time systems. In addition to his primary role in AI orchestration, he acts as a university lecturer. His research interests bridges robotics, particularly humanoid posture control and human-robot interaction, with advanced statistical and deep learning methodologies.
|
|
Ndivhuwo Makondo
IBM Research, University of the Witwatersrand
South Africa
|
|
|
|
Brief Bio
Dr. Ndivhuwo Makondo is a Research Scientist and Manager in Data and AI at IBM Research – Africa, and a Visiting Researcher in Robotics at Wits University, South Africa, where he is also affiliated with the Robotics, Autonomous Intelligence Lab (RAIL) lab. He leads a multidisciplinary team advancing foundational and applied AI research spanning knowledge representation, reasoning, learning, natural language processing, and data management, contributing both to IBM’s global AI strategy and the localisation of advanced AI technologies across Africa. His previous work at IBM included leading research on learnable reasoning to integrate structured knowledge and formal reasoning into neural systems. Before joining IBM, he was a Robotics Researcher at the CSIR’s Mobile Intelligent Autonomous Systems group, where he led efforts on vision and control algorithms for mobile manipulators in complex environments and worked on learning robot kinematic and dynamic models for low-level control.
|
|
Leonard Johard
Calejo Hybrid Intelligence AB
Sweden
|
|
|
|
Brief Bio
Leonard Johard received his PhD from SSSUP's PERCRO lab and has since been working with distributed brain simulators at CERN Openlab and been active as an inventor in the startup world. He co-founded computer vision retail analysis company Indivd AB and hybrid physics/AI intelligence startup Calejo Hybrid Intelligence AB.
|
SCOPE
This special session focuses on the intersection of physical sciences, control engineering, and artificial intelligence. The scope encompasses the development, analysis, and application of gray-box modeling, approaches that strategically combine physical laws, domain knowledge, and first principles with the flexibility of modern data-driven AI. The session aims to bring together researchers and practitioners developing methods that are both intelligent and accountable, targeting safety-critical, data-scarce, or highly complex domains (such as industrial automation, healthcare, scientific discovery, and robotics) where purely black-box models are insufficient, and purely white-box models fail to scale.
TOPICS OF INTEREST
Topics of interest include, but are not limited to:
- Hybrid and Gray-Box Modeling
- Integration of physics-based principles, constraints, and domain knowledge with neural networks
- Physics-Informed Neural Networks (PINNs) for modeling, simulation, and control
- System Modeling, Control, and Digital Twins
- System identification and parameter estimation using hybrid models
- Controllers combining first-principles and data-driven components
- High-fidelity digital twins for optimization
- Applications in Industry, Medicine, and Science
- Predictive maintenance and process optimization
- Biomechanical models combined with AI for personalized medicine;
- Hybrid models for inverse problems in physics, chemistry, and climate science
- Human-Centric and Safety-Critical AI
- Human-in-the-loop systems
- Safety, robustness, and certification of AI systems where hallucinations or failures are unacceptable
- Explainability, Robustness, and Evaluation: Methods for interpretability, uncertainty quantification, and stability analysis in hybrid models
- Benchmarks for evaluating hybrid intelligence in real-world settings
IMPORTANT DATES
Paper Submission:
July 31, 2026
Authors Notification:
September 9, 2026
Camera Ready and Registration:
September 18, 2026
SPECIAL SESSION PROGRAM COMMITTEE
Martin Ciupa,
MindMaze, Switzerland
Elena Gramellini,
Univ. of Manchester, United Kingdom
Ines Schweigert,
Jonas & Redmann, Germany
Riccardo di Sipio,
Dayforce, ex-CERN, Canada
Claudio Zito,
School of Mathematical and Computer Sciences, Heriot-Watt University, United Arab Emirates
(list not yet complete)
PAPER SUBMISSION
Prospective authors are invited to submit papers in any of the topics listed above.
Instructions for preparing the manuscript (in Word and Latex formats) are available at: Paper Templates
Please also check the Guidelines.
Papers must be submitted electronically via the web-based submission system using the appropriated button on this page.
PUBLICATIONS
After thorough reviewing by the special session program committee, all accepted papers will be published in a special section of the conference proceedings book - under an ISBN reference and on digital support - and submitted for indexation by SCOPUS, Google Scholar, DBLP, Semantic Scholar, EI and Web of Science / Conference Proceedings Citation Index.
SCITEPRESS is a member of CrossRef (http://www.crossref.org/) and every paper is given a DOI (Digital Object Identifier).
All papers presented at the conference venue will be available at the SCITEPRESS Digital Library