An evolutionary navigator for autonomous agents on unknown large-scale environments

Abstract

Computation of a collision-free path for a movable object among obstacles is an important problem in the fields of robotics. In previous research we have introduced an evolutionary algorithm for a robot moving on a known map considering a 4-connected grid model, and we have obtained encouraging results. In this paper, we focus our attention on a more complex motion planning problem: An autonomous agent with a limited sensor capability which is moving in a completely unknown large-scale environrnent. We introduce an evolutionazy approach that has shown some adaptation abilities due to its constant update of its environrnent knowledge, and replanning only when it is strictly required. We compare our approach for vazious map sizes to a very well-known evolutionazy algorithm and to the complete approach D* Lite. Our algorithm outperforms them in both CPU time and in the number of re-plannings. © 2008 TSI® Press.