Goal-Directed Imitation in a Humanoid Robot

Abstract— Our work aims at developing a robust discriminant controller for robot programming by demonstration. It addresses two core issues of imitation learning, namely “what to imitate” and “how to imitate”. This paper presents a method by which a robot extracts the goals of a demonstrated task and determines the imitation strategy that satis es best these goals. The method is validated in a humanoid platform, taking inspiration of an in uential experiment from developmental psychology.

• Type: Conference
• Year: 2005
• Where: ICRA
• Authors: Sylvain Calinon, Florent Guenter, Aude Billard
• Keywords: ICRA 2005, Imitation Strategy, Robot Programming, Robotics, Robust Discriminant Controller