Learning and communication via imitation: an autonomous robot perspective

Abstract

This paper proposes a neural network architecture designed to exhibit learning and communication capabilities via imitation. Our architecture allows a "protoimitation" behavior using the "perception ambiguity" inherent in real environments. In the perspective of turn-taking and gestural communication between two agents, new experiments on movement synchronization in an interaction game are presented. Synchronization is obtained as a global attractor depending on the coupling between agents' dynamics. We also discuss the unsupervised context of the imitation process and present new experiments in which the same architecture is able to learn perception-action associations without any explicit reinforcement. The learning is based on the ability to detect novelty or irregularities in the communication rhythm.