Seminar: Dynamic Real-world Reinforcement Learning through Muscular Robots, Dr. Dieter Büchler from Max Planck Institute for Intelligent Systems

Abstract: Despite decades of robotics research, current robots still struggle to acquire general and flexible dynamic skills on human level. Tasks, such as table tennis, represent this set of dynamic problems that appear easy to learn for humans but pose a steep challenge for anthropomorphic robots. In this talk, I will argue that hardware plays a crucial role for the generation of such skills. In particular, muscular actuation (i) enables robust long-term training such as required with reinforcement learning and (ii) fail-safe execution of explosive motions that allow robots to safely explore in dynamic regimes. Stay tuned for table tennis playing, ball smashing and precisely controlled soft muscular robots.

Video: https://youtu.be/GQtpSMEpn5A

Bio: Dieter Büchler is a research group leader at the Max Planck Institute for Intelligent Systems within the Empirical Inference department in Tübingen (Germany) led by Bernhard Schölkopf. Previously, Dieter received his Ph.D. from the Technische Universität Darmstadt in 2019 under the supervision of Jan Peters, an M.Sc. in Biomedical Engineering from the Imperial College London, and a B.Eng. in Information and Electrical Engineering from the HAW Hamburg (Germany). His research interests are in the areas of control, machine learning and robotics for soft robots.