Towards efficient algorithms for robust multi-contact behaviors
Speaker: Prof. Ludovic Righetti, Machines in Motion Lab @ NYU
July 27 1pm EDT
Register for the UofT Robotics Newsletter to learn more about our Seminar Series – seminars are open to all UofT students and faculty.
Abstract:
Reasoning about physical interactions is a computationally daunting task, yet contacts are at the core of any manipulation or locomotion behavior. For this reason, robots try to avoid physical interactions at all costs and unexpected physical contacts often lead to failures. This is in stark contrast with humans or animals, that not only constantly interact with their environment but also exploit this interaction to their advantage. This talk will present our efforts towards breaking this complexity, leveraging both optimal control and reinforcement learning. First, we will argue that understanding the structure underlying physical interactions is key to devising computationally efficient algorithms that generate complex multi-contact motions. Then we will discuss our recent approaches to ensure that multi-contact behaviours are robust to environmental uncertainty. Experimental results with legged robots, in particular our open-source torque controlled quadruped robot, will illustrate the performance of our approach as well as important remaining challenges.
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 and a Senior Researcher at the Max-Planck Institute for Intelligent Systems in Germany. He holds an engineering diploma in Computer Science and a Doctorate in Science from the Ecole Polytechnique Fédérale de Lausanne, Switzerland. He was previously a postdoctoral fellow at the University of Southern California prior to starting the Movement Generation and Control Group at the Max-Planck Institute for Intelligent Systems in Germany. He has received several awards, most notably the 2010 Georges Giralt PhD Award, the 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems Best Paper Award, the 2016 IEEE Robotics and Automation Society Early Career Award and the 2016 Heinz Maier-Leibnitz Prize. His research focuses on the planning and control of movements for autonomous robots, with a special emphasis on legged locomotion and manipulation. He is more broadly interested in questions at the intersection of decision making, optimization and machine learning and their applications to physical systems.