Skip navigation
PDF 3.2 MB
Pages 771-777
First published 30 July 2014

Neuroevolution of sequential behavior in multi-goal navigation task

Sergey Muratov, Konstantin Lakhman and Mikhail Burtsev

Abstract (Excerpt)

In this paper we consider a problem of evolutionary generation of behavioral sequences for a mobile robot in the environment with multiple goals. Many real-world tasks can be abstracted in terms of generation of actions sequences. To address this problem we utilize a neuroevolutionary algorithm, based on a neuron duplication, as a method to generate the robot's controller for multi-goal sequential navigation. We show that neuroevolution produces stable behavioral strategies that can be successfully utilized even in the case of changing or randomized environment.