Robot Learning for Physical Intelligence:
Trends, Challenges and Integration
Half-day Workshop @ IEEE/ASME International Conference
on Advanced Intelligent Mechatronics (AIM 2026)
July 7th, 2026 - HH:MM CEST - Genova, Italy
Abstract
Robotic and mechatronic systems are increasingly infused with learning-based components, yet the majority of deployed robots remain narrowly trained, task-specific, and fragile when operating outside controlled conditions. Within the broad research vision of Physical AI, this limitation reflects a deeper issue: intelligence in physical systems cannot be reduced to isolated algorithms but must emerge from the tight coupling of learning paradigms with mechatronic embodiments. In this context, three intertwined learning approaches are rapidly reshaping adaptive robotics - generative AI, continual (lifelong) learning, and imitation and reinforcement learning - by enabling world modelling and reasoning, long-term adaptation from experience, and skill acquisition through interaction and demonstration.
The goal of the workshop is to connect recent advances in these robot learning paradigms with the realities of intelligent mechatronic systems, including real-time operation, limited compute and energy budgets, safety constraints, and human–robot interaction. By highlighting experimentally validated systems, discussing failure modes and evaluation practices, and promoting shared benchmarks, the workshop aims to distil common challenges, identify emerging system-level design principles, and foster community alignment toward reproducible, scalable, and physically grounded robotic intelligence.
Organizers
 |  |  |  |  |
PostDoctoral Researcher BRAIR Lab @ The BioRobotics Institute, Sant'Anna School of Advanced Studies, Italy | PhD Student Institut für Informatik @ Humboldt-Universität zu Berlin, Germany | Full Professor Institut für Informatik @ Humboldt-Universität zu Berlin, Germany | Associate Professor Department of AI, Data and Decision Sciences, LUISS Guido Carlo University, Italy | Associate Professor BRAIR Lab @ The BioRobotics Institute, Sant'Anna School of Advanced Studies, Italy |
Topics
- Physical AI, Sensory Representation, Motor Control
- Continual (Lifelong) Learning, Online Learning
- Generative AI, Foundation Models, Large Language Models
- Imitation Learning, Reinforcement Learning
- Robotics, Adaptive Systems
Invited speakers (confirmed)
Vincenzo Lomonaco Associate Professor
COLLAGE Lab Department of AI, Data and Decision Sciences, LUISS Guido Carlo University, Italy | Talk: The Future of Continual Learning in the Era of Foundation Models: Three Key Directions Abstract. TBC Short Bio. Vincenzo is Associate Professor in the Department of AI, Data and Decision Sciences at Luiss Guido Carli University, where he leads the Collage Lab. He is also the co-founder of ContinualIST, a spin-off of the University of Pisa, a founding member of the non-profit organization ContinualAI, and the Principal Investigator of several research projects and industrial collaborations. In just six years of research following his PhD, he has secured over €2 million in funding, including the prestigious Italian Science Fund (FIS) – Starting Grant, a PRIN, and collaborations with international organizations such as Intel, Meta, Leonardo, and ESA. Over the past decade, he has published more than 80 scientific papers in top-tier conferences and journals on the topic of Sustainable Artificial Intelligence. His pioneering research in continual and decentralized machine learning has been recognized with the prestigious Marco Somalvico Award 2025 from the Italian Association for Artificial Intelligence. |
Verena V. Hafner Full Professor
Institut für Informatik Humboldt-Universitat zu Berlin, Germany | Talk: Continual Learning for a Robotic Self Abstract. TBC Short Bio. Verena is Full Professor at Humboldt-Universitat zu Berlin, she has led numerous EU projects on developmental robotics. Her research explores lifelong learning and autonomous knowledge structuring through physical and social interaction. |
Sylvain Calinon Senior Research Scientist  Idiap Research Institute & EPFL, Switzerland | Talk: Frugal Learning for Physical Human-Robot Collaboration Abstract. Despite significant advances in AI, robots still struggle with tasks involving physical interaction. Robots can easily beat humans at board games such as Chess or Go but struggle to skillfully move the game pieces by themselves (the part of the task that humans subconsciously succeed in). Learning manipulation skills is both hard and fascinating because the movements and behaviors to acquire are tightly connected to our physical world and to embodied forms of intelligence. I will present an overview of representations and learning approaches that can help robots acquire manipulation skills through physical human-robot collaboration. I will present the advantages of targeting a frugal learning approach, where the term "frugality" has two goals: 1) learning manipulation skills from only few demonstrations or exploration trials; and 2) learning only the components of the skill that really need to be learned. Toward this goal, I will emphasize the roles of geometry, manifolds, implicit shape representations and distance fields as inductive biases to facilitate human-guided manipulation skill acquisition. I will also show how ergodic control can provide a mathematical framework to generate exploration and coverage movement behaviors, which can be exploited by robots as a way to cope with uncertainty in sensing, proprioception and motor control. Short Bio. Sylvain is a Senior Research Scientist at the Idiap Research Institute and a Lecturer at the Ecole Polytechnique Fédérale de Lausanne (EPFL). He heads the Robot Learning & Interaction group at Idiap, with expertise in human-robot collaboration, robot learning from demonstration, geometric representations and optimal control. The approaches developed in his group can be applied to a wide range of applications requiring manipulation skills, with robots that are either close to us (assistive and industrial robots), parts of us (prosthetics and exoskeletons), or far away from us (shared control and teleoperation). |
Jean H. Oh Associate Research Professor 
roBot Intelligence Group Carnegie Mellon Universit, USA | Talk: Creative Physical AI Abstract. Do robots need creativity? I will share my stance that they do need creativity to solve general problems and support human values. Physical AI is a type of AI that enables robots to perceive and interact with a physical world. Trendy approaches in physical AI such as Vision-Language-Action (VLA) models directly map the observations to actions where robots make decisions dominantly based on sensed information. While sensing is crucial for understanding the current physical environments, this paradigm of physical AI is fundamentally limited to support general tasks where humans see around corners and solve problems creatively based on not only what they can observe now but also various predictions of the latent spatiotemporal and social contexts. I will illustrate the examples where robots without creativity can fail to fulfill even simple goals and how we can develop physical AI for creative problem solving. If equipped with creative physical AI, can such robots promote human creativity as in creating arts? Generative AI has brought us numerous types of convenience in the digital art world. To create artifacts in the real world, creative physical AI is needed, for instance, to preserve traditional craftsmanship such as wood carving or claymation, which faces declining participation due to its labor-intensive nature. More broadly, our innovations in creative physical AI aim to encourage people to participate in more creative activities such as educational and therapeutic art sessions. I would like to invite the audience to think about how we can use technologies to promote human creativity for the next generation. Short Bio. Jean is Associate Research Professor at Carnegie Mellon University, she develops Creative Physical AI systems for safe and socially aware robot behavior. Her award-winning research focuses on social robot navigation and embodied intelligence. |
Egidio Falotico Associate Professor BRAIR Lab The BioRobotics Institute, Scuola Superiore Sant'Anna, Italy | Talk: Brain-Inspired Robot Learning: Adaptation, Memory and Interaction Abstract. TBC Short Bio. Egidio is Associate Professor at Scuola Superiore Sant’Anna, where he specializes in brain-inspired robot motor control and sensorimotor coordination. He focuses on integrating cognitive models with (soft) robots to test coherence, persistence, and adaptability of learned behaviours. |
Schedule [tentative] (9am to 1pm CEST)
Time | Activity | Speaker |
| 9.00am - 9.15am | Welcome and Speakers Presentation | Organizers |
| 9.15am - 9.45am | Talk: The Future of Continual Learning in the Era of Foundation Models: Three Key Directions + Q&A | Vincenzo Lomonaco |
| 9.45am - 10.15am | Talk: Continual Learning for a Robotic Self + Q&A | Verena V. Hafner |
| 10.15am - 10.45am | Talk: Frugal Learning for Physical Human-Robot Collaboration + Q&A | Sylvain Calinon |
| 10.45am - 11.00am | Pitch of Selected Contributions | TBD |
| 11.00am - 11.30am | Coffee Break and Poster Session | |
| 11.30am - 12.00pm | Talk: Brain-Inspired Robot Learning: Adaptation, Memory and Interaction + Q&A | Egidio Falotico |
| 12.00pm - 12.30pm | Talk: Creative Physical AI + Q&A | Jean H. Oh |
| 12.30pm - 1.00pm | Interactive Panel Discussion and Conclusion | All |
Call for Contributions
Link for submission - Deadline: May 31st, 2026
We invite young researchers and students to submit an extended abstract (max 2 pages, IEEE A4 format) including contributions on Physical AI with focus on - but not limited to - (i) Continual Robot Learning, (ii) Generative AI for perception, planning, and control, (iii) Imitation and Reinforcement Policy Learning and (iv) Advanced Robot Learning strategies and benchmarks.
Authors of selected abstracts will be invited to present their work with a pitch talk and a poster (A0 size, portrait) during the coffee break/poster session.
If you have additional questions, please contact: enrico.donato@santannapisa.it