Chaotic evolutionary processing and its applications

Abstract

Proposes the realization of evolutionary computation by chaotic dynamics instead of conventional genetic algorithms for such intelligent agents as welfare robots which assist humans. This evolutionary computation is realized by applying chaotic retrieval on associative memories. We apply this evolutionary computation to multi-agent robots which move abreast. Essentially, the process of this evolutionary computation is parallel processing. Therefore, we implement its parallel processing algorithm on an A-NET(Actors NETwork) parallel object-oriented computer, and show the usefulness of parallel processing for the proposed evolutionary computation.