Imitation: learning and communication

Pierre Andry (1) , Sorin Moga (2) , Philippe Gaussier (1) , Arnaud Revel (1) , Jacqueline Nadel (3)

1 ETIS - UMR 8051 - Equipes Traitement de l'Information et Systèmes
2 LUSSI - Département Logique des Usages, Sciences sociales et Sciences de l'Information
3 VAP - Vulnérabilité Adaptation et Psychopathologie

This paper focuses on our works on imitation in autonomous robots. In a first part, we take into account recent studies in the field of developmental psychology and consider the two functions of imitation (learning and communication) that these studies have stressed. In a second part, we propose the idea that a proto imitative behavior can be induced in a mobile robot via a limitation of its visual perception. We provide a robotic implementation in which a mobile robot recognizes its teacher's image. Finally, we discuss imitation in a non-supervised context and we propose a simple system which learns motor associations with non explicit reinforcement on the basis of its ability to detect novelty.

Mots clés: Intelligence artificielle et robotique; Apprentissage; Communication homme machine; Machines intelligentes et robotique; Perception et représentations

Domaines: Informatique

Pierre Andry, Sorin Moga, Philippe Gaussier, Arnaud Revel, Jacqueline Nadel. Imitation: learning and communication. The Sixth International Conference on Simulation of Adaptive Behavior, 2000, France. pp.353-362. ⟨hal-00426253⟩