Machine Learning and Robotics

Daniel D. Lee: Dept. of Electrical and Systems Engineering, University of Pennsylvania

Abstract

How can you get a robot to do what you want?  Even with recent advances in computational, sensory, and motor hardware, there remains the difficult problem of programming robots to perceive and respond to the external world.  It is impossible to pre-script the robot with all possible scenarios in a changing environment.  Instead, we would like the robot to learn from its actions and to get better over time.  I will review some recent advances in machine learning algorithms, and their application to robot perception, navigation, and motor control.

Short Biography

Daniel Lee : Daniel Lee is currently an Associated Professor in the School of Engineering and Applied Science at the University of Pennsylvania. He studied physics receiving his A.B. from Harvard in 1990 and his Ph.D. in condensed matter physics from MIT in 1995. After completing my studies, he joined Bell Labs, the research and development arm of Lucent Technologies, where he was a researcher in the Theoretical Physics and Biological Computation departments. After six years in industrial research, he joined the faculty at Penn in 2001 where he is currently doing research and teaching in the Electrical and Systems Engineering Department and at the GRASP Lab.