Skip to Main content Skip to Navigation
New interface
Conference papers

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.
Document type :
Conference papers
Complete list of metadata

Cited literature [21 references]  Display  Hide  Download
Contributor : Marc Schoenauer Connect in order to contact the contributor
Submitted on : Thursday, January 29, 2015 - 2:09:21 PM
Last modification on : Sunday, June 26, 2022 - 12:02:49 PM
Long-term archiving on: : Friday, September 11, 2015 - 9:36:47 AM


Files produced by the author(s)




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⟩



Record views


Files downloads