Control and Imitation in Humanoids

Abstract

Humanoid robots will increasingly become a part of human everyday lives, but require more natural and simplified methods for control and humanrobot interaction. Our approach to addressing these challenges is to use biologically inspired notions of behavior-based control, and endow robots with the ability to imitate, so that they can be programmed and interacted with through demonstration and imitation. Our approach to the problem, based on neuroscience evidence, structures the motor system into a collection of primitives, which are then used to both generate the humanoid 's movement repertoire and provide prediction and classification capabilities for visual perception and interpretation. Thus, what the humanoid can do helps it understand what it sees, and vice versa. We describe the behavior-based background of our work and the neuroscience evidence on which our humanoid motor control and imitation model is based. Next we describe our use of human movement data as ...