 |
    |
Coupling Evolution and Information Theory for Autonomous Robotic Exploration
Guohua Zhang1, 2 and Michèle Sebag2
1Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu 610041, China
2TAO, CNRS – INRIA – LRI, Université Paris-Sud, 91128, Orsay Cedex, France
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 controller, 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.
Keywords: Evolutionary robotics, information theory, intrinsic motivation, entropy
LNCS 8672, p. 852 ff.
lncs@springer.com
© Springer International Publishing Switzerland 2014