|
Abstract : |
part of our everyday lives, they will serve as caretakers for the elderly and disabled, assistants in surgery and rehabilitation, and educational toys. But for this to happen, programming and control must become simpler and human?robot interaction more natural. Both challenges are particularly relevant to humanoid robots, which are highly difficult to control yet most natural for interaction with people and operation in human environments. As this article shows, we have used biologically inspired notions of behavior-based control to address these challenges at the University of Southern California?s Interaction Lab, part of the USC Robotics Research Labs. By endowing robots with the ability to imitate, we can program and interact with them through human demonstration, a natural human?humanoid interface. The human ability to imitate?to observe and repeat behaviors performed by a teacher?is a poorly understood but powerful form of skill learning. Two fundamental open problems in imitation involve interpreting and understanding the observed behavior and integrating the visual perception and movement control systems to reconstruct what was observed. Our research has a similarly twofold goal: we are developing methods for segmenting, |
