Control theory has an answer for just about everything, but seems to fall short when it comes to closing a feedback loop using a camera, dealing with the dynamics of contact, and reasoning about robustness over the distribution of tasks one might find in the kitchen. Recent examples from reinforcement and imitation learning demonstrate great promise, but don’t leverage the rigorous tools from systems theory. I’d like to discuss why, and describe some recent results of closing feedback loops from pixels for “category-level” robot manipulation. In particular, I will introduce a strong formulation for a new problem -- finding the shortest path in a graph of convex sets -- that captures the fundamental hardness inherent in contact planning problems.
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.
Host: Professors Prashant Mehta and Joao Ramos