Emergent Functionality in Robotic Agents through On-Line Evolution

Abstract

The paper proposes an architecture for the online evolution of new behavioral competences on a robotic agent. Some experimental results for evolving a set of primitive behaviors are presented. Introduction A central question in ALife research is how new complexity and new functionality may emerge [Steels1994]. Selectionism and self-organisation have so far been put forward as the key explanatory principles [Langton1989]. These principles have been been applied at many level of biological systems, from the chemical reactions that explain the origin of life [Kaufmann1993] to the interaction between individuals in societies [Deneubourg1993]. This paper explores in how far selectionism and selforganisation may lead to the build up of behavioral complexity in animals. In the tradition of Alife research, this exploration takes place by building artificial systems, i.c. robotic agents. There has already been a large amount of work attempting to use selectionist techniques for evolving behavi...