Teaching and Working with Robots as a Collaboration

Abstract

New applications for autonomous robots bring them into the human environment where they are to serve as helpful assistants to untrained users in the home or office, or work as capable members of human-robot teams for security, mil-itary, and space efforts. These applications require robots to be able to quickly learn how to perform new tasks from natural human instruction, and to perform tasks collabora-tively with human teammates. Using joint intention theory as our theoretical frame-work, our approach integrates learning and collaboration through a goal based task structure. Specifically, we use col-laborative discourse with accompanying gestures and so-cial cues to teach a humanoid robot a structurally com-plex task. Having learned the representation for the task, the robot then performs it shoulder-to-shoulder with a hu-man partner, using social communication acts to dynami-cally mesh its plans with those of its partner, according to the relative capabilities of the human and the robot. 1.