Legged locomotion has inspired some of the deepest and richest understanding we have for contact-rich dynamics and control. But we have so far gotten away with simplifying assumptions that don’t scale to more complex scenarios. Scaling up requires thinking about significantly more complicated contact geometries, a wider range of inertial scales, and *most importantly* severe partial observability and model uncertainty. Our rigorous formulations make tasks that really should be easy look almost insurmountably difficult. In this talk, I’ll try to share some lessons from pursuing contact-rich dynamics and control for “open-world” manipulation.
Russ Tedrake is the Toyota Professor of Electrical Engineering and Computer Science, Aeronautics and Astronautics, and Mechanical Engineering at MIT, the Director of the Center for Robotics at the Computer Science and Artificial Intelligence Lab, and the leader of Team MIT’s entry in the DARPA Robotics Challenge. He is also the Vice President of Robotics Research at Toyota Research Institute (TRI). Dr. Tedrake is a recipient of the NSF CAREER Award, the MIT Jerome Saltzer Award for undergraduate teaching, the DARPA Young Faculty Award in Mathematics, the 2012 Ruth and Joel Spira Teaching Award, and was named a Microsoft Research New Faculty Fellow.