Learning, perception and control for robotics
Our research focuses on developing novel learning, perception, motion planning and control algorithms to tackle challenging real-world robotics problems. Application areas of particular interest inspiring out algorithmic work include, but are by no means limited to, personal robotics, surgical robotics, and autonomous flight. We have successfully developed techniques to enable a quadruped robot to traverse challenging, previously unseen terrains; to enable a helicopter to perform by far the most challenging aerobatic maneuvers performed by any autonomous helicopter to date, including maneuvers such as chaos and tic-tocs, which only exceptional expert human pilots can fly; to enable a personal robot to fold towels and sort socks.
More information: http://www.cs.berkeley.edu/~pabbeel