Coupling Evolution and Information Theory for Autonomous Robotic Exploration - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Coupling Evolution and Information Theory for Autonomous Robotic Exploration

Résumé

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.
Fichier principal
Vignette du fichier
guohaoPPSN2014-author2.pdf (813.51 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01109770 , version 1 (29-01-2015)

Identifiants

Citer

Guohua Zhang, Michèle Sebag. Coupling Evolution and Information Theory for Autonomous Robotic Exploration. Parallel Problem Solving from Nature — PPSN XIII, Sep 2014, Ljubliana, Slovenia. pp.852 - 861, ⟨10.1007/978-3-319-10762-2_84⟩. ⟨hal-01109770⟩
230 Consultations
297 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More