Plenary-Keynote Talks

Jens Kober

Delft University of Technology

Robots Learning Through Interactions

Abstract: The acquisition and self-improvement of novel motor skills is among the most important problems in robotics. Complexity arises from interactions with their environment and humans. A human teacher is always involved in the learning process, either directly (providing data) or indirectly (designing the optimization criterion), which raises the question: How to best make use of the interactions with the human teacher to render the learning process efficient and effective? I will discuss various methods we have developed in the fields of supervised learning, imitation learning, reinforcement learning, and interactive learning and illustrate those with real robot experiments ranging from fun (ball-in-a-cup) to more applied (retail environments).

Biography: Jens Kober is an associate professor at the TU Delft, Netherlands. He worked as a postdoctoral scholar jointly at the CoR-Lab, Bielefeld University, Germany and at the Honda Research Institute Europe, Germany. He graduated in 2012 with a PhD Degree in Engineering from TU Darmstadt and the MPI for Intelligent Systems. For his research he received the annually awarded Georges Giralt PhD Award for the best PhD thesis in robotics in Europe, the 2018 IEEE RAS Early Academic Career Award, the 2022 RSS Early Career Award, and has received an ERC Starting grant. His research interests include motor skill learning, (deep) reinforcement learning, imitation learning, interactive learning, and machine learning for control.

Katja Mombaur

Karlsruhe Institute of Technology

Endowing Humanoid Robots with Motion Intelligence: the Roles of Bio-inspiration, Models, Optimization and Learning

Abstract: In recent years, the field of humanoid robotics has made remarkable progress, with numerous new prototypes emerging from both industry and academic research labs around the world and presenting new skills every day. The vision of humanoid robots assisting humans in a wide range of dirty, dull, and dangerous tasks—and even serving as companions or caregivers—is steadily becoming more attainable. Nevertheless, generating and controlling whole-body motions in bipedal humanoid robots remains a significant challenge due to their complex nonlinear dynamics, a high number of degrees of freedom, underactuation, and inherent instability. As a result, humanoid robots still fall short of achieving human-level motor skills in many situations. In this talk, I will give an overview of our research on endowing humanoid robots with motion intelligence or embodied artificial intelligence that makes the robot aware of how it moves in and interacts with its dynamic environment and with humans, including physical and social aspects of human-robot interaction. Our research seeks to uncover and describe fundamental principles of human movement, such as stability, efficiency, and the optimization strategies underlying specific behaviors, and to gain insight into human preferences when interacting with a robot. We aim not only to achieve a qualitative understanding, but also to gain precise, quantitative insights that can be captured through mathematical models. These models can serve as sources of bioinspiration for humanoid motion and also help interpret human intent. Building on this foundation, we develop efficient computational methods that integrate model-based techniques, such as optimization, with model-free approaches. This combination enables the generation and refinement of humanoid movements tailored to specific situations. I will show different examples from our research, such as walking on different terrains, balancing, using personal transporters, bimanual manipulation of objects, and  interactions with humans at close proximity during dancing or medical applications.

Biography: Katja Mombaur joined the Karlsruhe Institute of Technology (KIT) in Germany in 2023 as Full Professor, Chair for Optimization & Biomechanics for Human-Centred Robotics and Director of the BioRobotics Lab. In addition, she holds an affiliation with the University Waterloo in Canada where she has been Full Professor and Canada Excellence Research Chair (CERC) for Human-CentredRobotics & Machine Intelligence since 2020. Prior to moving to Canada, she has been a Full Professor at Heidelberg University where she directed the Optimization, Robotics & Biomechanics Chair, as well as the Heidelberg Center for Motion Research. Her international experience includes two years as a visiting researcher at LAAS-CNRS in Toulouse and one year at Seoul National University. She studied Aerospace Engineering at the University of Stuttgart and SupAéro in Toulouse and holds a PhD in Mathematics from Heidelberg University. ​ Katja Mombaur currently serves as the Vice President for Member Activities of the IEEE Robotics & Automation Society and as Senior Editor of the IEEE Transactions on Robotics and has actively contributed to the organization of many conferences and workshops. She is the KIT Spokesperson of the Helmholtz Graduate School of Information and Data Science for Health (HIDSS4Health).   ​Katja’s research focuses on understanding human movement by a combined approach of model-based optimization, learning and experiments and using this knowledge to improve motions of humanoid robots and the interactions of humans with exoskeletons, prostheses and external physical devices. Her goal is to endow humanoid and wearable robots with motion intelligence that allow them to operate safely in a complex human world. The development of efficient algorithms for motion generation, control and learning is a core component of her research.