Robots are evolving from stationary devices that perform manufacturing tasks to mobile, information gathering, computing, and decision making platforms. The autonomous vehicles participating in the DARPA Grand Challenges highlighted the significant progress that has been made in this area and the enormous work that remains to be done. At the University of Michigan, we are exploring the feedback control principles of bipedal robotic locomotion, with the goal of endowing machines with the ability to walk on two legs with the agility of a human. We also use artificial intelligence techniques for dealing with planning and uncertainty, localization and mapping, sensor processing and classification, and continuous learning.