An experimental comparison of imitation paradigms used in social robotics

Abstract

We study and contrast particular issues arising in two social learning paradigms that are widely used in robotics research: (i) following or matched-dependent behaviour and (ii) static observational learning. Experiments are carried out with physical Khepera robots whose controllers include motor schemas and the new neural network based methods for model agent-centred perception of angle and distance. The robots are trained to perceive the dynamic movement of a human or robot demonstrator carrying a light source. The robots learn the behaviour either through the perception from a static location or while following. The differences and implications of the results of both the following and observation mechanisms are compared and contrasted.