Analysis of Neurocontrollers Designed by Simulated Evolution

Randomized, adaptive, greedy search using evolutionary algorithms ooers a powerful and versatile approach to the automated design of neural network architectures for a variety of tasks in artiicial intelligence and robotics. In this paper we present results from the evolutionary design of a neuro-controller for a robotic bulldozer. This robot is given the task of clearing an arena littered with boxes by pushing boxes to the sides. Through a careful analysis of the evolved networks we show how evolution exploits the design constraints and properties of the environment to produce network structures of high tness. We conclude with a brief summary of related ongoing research examining the intricate interplay between environment and evolutionary processes in determining the structure and function of the resulting neural architectures.