Imitation faculty based on a simple visuo-motor mapping towards interaction rule learning with a human partner

Abstract

Imitation has been regarded as one of the key technologies indispensable for communication since the mirror neuron made a sensation not only in physiology but also in other disciplines such as cognitive science, and even robotics. This paper is aimed at building a human-robot communication system and proposes an observation-to-motion mapping system as the first step towards the final goal of learning natural communication. This system enables a humanoid platform to imitate the observed human motion, that is, a mapping from observed human motion data to its own motor commands. To validate the effectiveness of the proposed system, we examine whether the robot can acquire the interaction rule in an environment in which a human motion occurs under an artificial interaction rule