Multi-agent Learning of Heterogeneous Robots by Evolutionary Subsumption

Hongwei Liu^1,2 and Hitoshi Iba¹

¹Graduate School of Frontier Science
The University of Tokyo
Hongo 7-3-1, Bunkyo-ku, Tokyo 113-8656, Japan

²School of Computer and Information
Hefei University of Technology
Hefei 230009 China
{Lhw,Iba}@miv.t.u-tokyo.ac.jp

Abstract. Many multi-robot systems are heterogeneous cooperative systems, systems consisting of different species of robots cooperating with each other to achieve a common goal. This paper presents the emergence of cooperative behaviors of heterogeneous robots by means of GP. Since directly using GP to generate a controller for complex behaviors is inefficient and intractable, especially in the domain of multi-robot systems, we propose an approach called Evolutionary Subsumption, which applies GP to subsumption architecture. We test our approach in an "eye"-"hand" cooperation problem. By comparing our approach with direct GP and artificial neural network (ANN) approaches, our experimental results show that ours is more efficient in emergence of complex behaviors.

LNCS 2724, p. 1715 ff.

Full article in PDF

lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2003