Coupling Evolution and Information Theory for Autonomous Robotic Exploration

Guohua Zhang 1, 2, 3 Michèle Sebag 2, 3
2 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : This paper investigates a hybrid two-phase approach toward exploratory behavior in robotics. In a first phase, controllers are evolved to maximize the quantity of information in the sensori-motor datastream generated by the robot. In a second phase, the data acquired by the evolved controllers is used to support an information theory-based con-troller, selecting the most informative action in each time step. The approach, referred to as EvITE, is shown to outperform both the evolutionary and the information theory-based approaches standalone, in terms of actual exploration of the arena. Further, the EvITE controller features some generality property, being able to efficiently explore other arenas than the one considered during the first evolutionary phase.
Type de document :
Communication dans un congrès
Thomas Bartz-Beielstein and Jürgen Branke and Bogdan Filipic and Jim Smith. Parallel Problem Solving from Nature — PPSN XIII, Sep 2014, Ljubliana, Slovenia. Springer Verlag, Lecture Notes in Computer Science, 8672, pp.852 - 861, 2014, Lecture Notes in Computer Science. 〈10.1007/978-3-319-10762-2_84〉
Liste complète des métadonnées

Littérature citée [21 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01109770
Contributeur : Marc Schoenauer <>
Soumis le : jeudi 29 janvier 2015 - 14:09:21
Dernière modification le : jeudi 5 avril 2018 - 12:30:12
Document(s) archivé(s) le : vendredi 11 septembre 2015 - 09:36:47

Fichier

guohaoPPSN2014-author2.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Guohua Zhang, Michèle Sebag. Coupling Evolution and Information Theory for Autonomous Robotic Exploration. Thomas Bartz-Beielstein and Jürgen Branke and Bogdan Filipic and Jim Smith. Parallel Problem Solving from Nature — PPSN XIII, Sep 2014, Ljubliana, Slovenia. Springer Verlag, Lecture Notes in Computer Science, 8672, pp.852 - 861, 2014, Lecture Notes in Computer Science. 〈10.1007/978-3-319-10762-2_84〉. 〈hal-01109770〉

Partager

Métriques

Consultations de la notice

239

Téléchargements de fichiers

203