Self-organization in embodied reconfigurable architectures.
Résumé
This paper describes a bio-inspired architectural approach to design highly adaptive and reconfigurable systems in the context of mobile robotics. The purpose is to design the hardware architecture of an intelligent controller for a robot that exhibits several behaviors such as landscape learning, obstacle avoidance, path planning, sensorimotor control. The Embodied Computing approach presented is employed in this context to in- tegrate the reconfiguration management as a part of the behavior of the global system. We propose a hardware implementation of the approach based on artificial neural networks.
Domaines
Systèmes embarqués
Origine : Fichiers produits par l'(les) auteur(s)
Loading...