Robot programming based on traditional computer programming languages has proved very difficult. It seems desirable to program robots in the same way we program people, by demonstrating the task and coaching the learner. This talk will discuss several ingredients in robot programming by demonstration, including memory-based learning, finding good task primitives, and finding new strategies to solve problems.
Christopher G. Atkeson received the M.S. degree in Applied Mathematics (Computer Science) from Harvard University and the Ph.D. degree in Brain and Cognitive Science from M.I.T. Chris joined the M.I.T. faculty in 1986, and moved to the Georgia Institute of Technology in 1994, where he is an Associate Professor in the College of Computing. He is a recipient of a National Science Foundation Presidential Young Investigator Award.