Adaptation Capability of Cognitive Map Improves Behaviors of Social Robots

Abdelhak Chatty (1) , Philippe Gaussier (2) , Ilhem Kallel (3) , Philippe Laroque (2) , A.M. Alimi (3)

1 Agents et systèmes intélligents, Neurocybernétique
2 ETIS - UMR 8051 - Equipes Traitement de l'Information et Systèmes
3 CEM Lab - ENIS - Département de Génie Électrique de Sfax [ENIS]

In this paper, we study the impact of the cognitive map's adaptation in the context of multi-robot system. This map governs the emergence of non-trivial behaviors and structures at both individual and social levels. In particular, we show that adding a simple imitation and deposit behavior allows the cognitive robots to adapt themselves in unknown environment to solve different navigation tasks. We show that in our architecture the individual discoveries in each robot (i.e., goals) can have an effect at the population level, which induce then a new learning at the individual level and reciprocally, from the individual to the population level. We performed a series of experimentations with robots and simulated agents to validate our system.

Domaines: Neurosciences; Adaptation et Systèmes auto-organisés [nlin.AO]

Abdelhak Chatty, Philippe Gaussier, Ilhem Kallel, Philippe Laroque, A.M. Alimi. Adaptation Capability of Cognitive Map Improves Behaviors of Social Robots. IEEE Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob 2012), Nov 2012, San Diego, United States. pp.1-6. ⟨hal-00752924⟩