Learning Reactive Neurocontrollers Using Simulated Annealing for Mobile Robots

Résumé : This paper presents a method based on simulated annealing to learn reactive behaviors. This work is related with multi-agent systems. It is a first step towards automatic generation of sensorimotor control architectures for completing complex cooperative tasks with simple reactive mobile robots. The controller of the agents is a neural network and we use a simulated annealing techniques to learn the synaptic weights. We’ll first present the results obtained with a classical simulated annealing procedure, and secondly an improved version that is able to adapt the controller to failures or changes in the environment. All the results have been experimented under simulation and with a real robot.
Type de document :
Communication dans un congrès
IROS: Intelligent RObots and Systems, Las Vegas, Nevada, IEEE, pp.674-679, 2003
Liste complète des métadonnées

Littérature citée [11 références]  Voir  Masquer  Télécharger

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00269482
Contributeur : Christine Carvalho de Matos <>
Soumis le : jeudi 3 avril 2008 - 08:12:19
Dernière modification le : jeudi 11 janvier 2018 - 06:14:31
Document(s) archivé(s) le : vendredi 21 mai 2010 - 01:15:37

Fichier

D174.PDF
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : lirmm-00269482, version 1

Collections

Citation

Philippe Lucidarme, Alain Liégeois. Learning Reactive Neurocontrollers Using Simulated Annealing for Mobile Robots. IROS: Intelligent RObots and Systems, Las Vegas, Nevada, IEEE, pp.674-679, 2003. 〈lirmm-00269482〉

Partager

Métriques

Consultations de la notice

81

Téléchargements de fichiers

87