Warning: the event is not opened to the general public and limited to staff members.
Abstract: To walk, run, jump or manipulate objects, robots need to constantly interact with objects and the environment. Unfortunately, reasoning about physical interactions is a computationally daunting task. For this reason, robots try to avoid physical interactions at all costs and unexpected physical contacts often lead to failures. In this talk, I will present our approach(es) to break down this complexity: the formulation of optimal control problems that leverage machine learning and numerical optimization to achieve real-time efficiency and real-robot robustness. I will also demonstrate our algorithms on real manipulation and locomotion examples. Finally, I will discuss current challenges towards real applications.
Short bio: Ludovic Righetti is an Associate Professor in the Electrical and Computer Engineering Department and in the Mechanical and Aerospace Engineering Department at the Tandon School of Engineering of New York University. He is also a visiting researcher at the LAAS-CNRS. He holds an Engineering Diploma in Computer Science and a Doctorate in Science from the Ecole Polytechnique Fédérale de Lausanne. He was previously a postdoctoral fellow at the University of Southern California and a group leader at the Max-Planck Institute for Intelligent Systems. His research focuses on the planning, control and learning of movements for autonomous robots, with a special emphasis on legged locomotion and manipulation.