Speakers & Talks
Tamim Asfour is full Professor of Humanoid Robotics and the Director of the High Performance Humanoid Technologies Lab (H2T) of the Institute of Anthropomatics and Robotics at the Karlsruhe Institute of Technology (KIT), Germany. His research focuses on the engineering 24/7 humanoid robotics. In particular, he studies the mechano-informatics of humanoids as the synergetic integration of informatics, artificial intelligence, and mechatronics into complete humanoid robot systems, which learn from humans, experience and interaction with the environment to perform versatile tasks in the real world. Tamim is the developer of the ARMAR humanoid robot family. He has been a visiting professor at Georgia Tech, at the Tokyo University of Agriculture and Technology, and at the National University of Singapore. He is the Editor-in-Chief of the Robotics and Automation Letters (RA-L), the Founding Editor-in-Chief of the IEEE-RAS Humanoids Conference Editorial Board, the Spokesperson of the Robotics Institute Germany (RIG), the president of the Executive Board of the German Robotics Society (DGR), and the scientific spokesperson of the KIT Center “Information · Systems · Technologies” (KCIST).
Title of the talk: Learning and Transferring Knowledge from Humans to Humanoids
Understanding human versatility and motion intelligence – characterized by the ability to perform a wide variety of tasks in a fast, elegant, and efficient way, to interact and learn in multiple ways, and to adapt to novel situations – has inspired research in humanoid robotics. However, the generation of robot behaviors with human-like motion intelligence and performance has yet to be achieved. The talk will present our work on engineering humanoid robot systems that learn complex manipulation tasks from human observation. First, we will present work on taxonomies for describing whole-body loco-manipulation and bimanual manipulation tasks, providing structured frameworks for the analyzing, representing and transferring human motor and action knowledge to humanoid robots. Second, we will present recent results on learning geometric constraints task constraints from a small number of human demonstration videos and incrementally update these constraints when new demonstrations are available.
Gentiane Venture is Professor of Robotics with the University of Tokyo and a cross appointed fellow with the National Institute of Advanced Industrial Science & Technology, Japan. Her research focuses on the dynamics of human, robots and the environment. Her group and her work are transdisciplinary to see robotics not as field with applications in certain areas but rather as an art of living together.
Title of the talk: Control in Humans and Robots: Benefits and Boundaries
Sylvain Calinon 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 and model-based optimization. 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).
Title of the talk: Frugal learning of whole-body manipulation skills from human demonstrations
Many applications in robotics would benefit from robots being able to learn manipulation skills from only few demonstrations or trials. This contrasts with the ongoing trend in machine learning of constantly increasing the amount of data required to learn tasks. The main challenge of acquiring manipulation skills from limited training data is to find inductive biases and representations that can be used in a wide range of tasks, which requires us to advance on several fronts, including data structures and geometric structures.
As example of data structures, I will discuss the use of tensor factorization techniques that can be used in global optimization problems to efficiently extract and compress information, while providing diverse human-guided learning capabilities (imitation and environment scaffolding). As examples of geometric structures, I will discuss the use of Riemannian geometry and geometric algebra in robotics, where prior knowledge about the physical world can be embedded within the representations of skills and associated learning algorithms.
Dagmar Sternad is University Distinguished Professor in Biology, Electrical and Computer Engineering and Physics at Northeastern University. She received her BS and MS in Movement Science and Linguistics from the Technical University and Ludwig Maximilians University of Munich and her PhD in Experimental Psychology from the University of Connecticut in 1995. After 13 years at the Pennsylvania State University, in 2008 she moved to Northeastern University in Boston where she holds an interdisciplinary appointment in the departments of Biology, Electrical and Computer Engineering, and Physics. She is also executive member of the Institute of Experiential Robotics at Northeastern. Her research is documented in over 200 peer-reviewed publications. Her research has been continuously supported by the National Institute of Health (MERIT award), National Science Foundation, American Heart Association, Office of Naval Research, and others. In 2022, she received a Fulbright Fellowship to work at the Santa Lucia Foundation in Rome, Italy. In 2023 her student and faculty mentoring was recognized with an Excellence in Mentoring Award by the College of Science at Northeastern.
Title of the talk: Stability and Predictability in Complex Object Control – A Task-Dynamic Approach
How do humans interact with their environment and the vast array of objects in their environment, such as reaching to drink from a glass without spilling or tying shoelaces? Our research has examined interactive skills in both virtual and real environments with the goal to understand real-life interactions with complex objects in the environment. To gain quantitative insights, we have developed a task-dynamic approach that starts with analysis of how the task constrains and enables actions and their improvement with practice. Based on mathematical analyses of the modeled task, we study how humans develop strategies that meet complex demands posed by the interactive dynamics. Using the task of transporting a “cup of coffee” in different degrees of simplification, we show that humans develop skill by: 1) increasing predictability of object dynamics, 2) exploiting solutions with dynamic stability, 3) channeling noise into task-irrelevant dimensions.
Daniel Leidner began his career at the German Aerospace Center (DLR) with his Diploma and Master's thesis in 2009-2010. He joined the Institute for Robotics and Mechatronics as a research scientist in 2011. By 2016, he became the coordinator of the Rollin' Justin humanoid robot team. Dr. Leidner later led the Semantic Planning group and the Fault-Tolerant Autonomy Architectures group. He earned his doctorate in AI and Robotics from the University of Bremen in 2017, graduating summa cum laude, and received the Georges Giralt PhD Award for the best doctoral thesis in robotics in Europe, as well as the Helmholtz Award for Doctoral Students. In 2019, he was named an Innovator Under 35 by Technology Review Germany for his work in AI and robotics. From October 2023 to July 2024, he served as a robotics consultant to the German government, shaping national AI-based robotics strategy. Since October 2024, he holds a collaboration professorship in Cognitive Robotics Manipulation at the University of Bremen, which also includes leading the Department of Autonomy and Teleoperation at DLR.
Title of the talk: Why Humanoid Robotics Are Key to Mars Exploration and How They Will Empower Astronauts
Christian Becker-Asano earned his Dr. rer. nat. from the University of Bielefeld in 2008 for his work on affect simulation (WASABI architecture) applied to the virtual human Max. He was a JSPS Pre-Doctoral Fellow in 2005 at the National Institute of Informatics, Tokyo, under Prof. Helmut Prendinger.
In June 2015, he became an independent research scientist at Bosch R&D in Renningen, and from March 2018 to February 2020, he was Product Owner of Intralogistic Robotics at Grow platform GmbH in Ludwigsburg.
Since March 2020, he has been a full professor of "Artificial Intelligence and Human-Machine Interaction" at Stuttgart Media University, where he founded the "Humanoid Lab" in 2021, home to the first German custom-designed android robot "Andrea."
Christian Becker-Asano (becker-asano.de)
Title of the talk: Emotion simulation and expression in Human-Android interaction in Germany