Talk covering some of our recent work (UW, 2015/3/18)
A talk covering some of our older work (CMU Robotics Institute Seminar, 2013/10/18)
Our current research is primarily studying deep learning for robotics, where learning could be from demonstrations (apprenticeship learning) or through the robot's own trial and error (reinforcement learning). Targeted application domains include autonomous manipulation, flight, locomotion and driving.
Here is a talk covering some of our older/earlier work:
Personal Robotics: Perception for the Manipulation of Socks (IROS2011)