Evolving neuro-modules and their interfaces to control autonomous robots

Abstract

An evolutionary algorithm for the creation of recurrent network structures is presented. The aim is to develop neural networks con-trolling the behaviour of miniature robots. Two neuro-modules are created separately using this evolutionary approach. The first neuro-module gives the agents the ability to move within an environment without colliding with obstacles. The second neuro-module provides the agents with a phototropic behaviour. The interaction of the neuro-modules is then investigated evolving the necessary interface to pro-vide the agents with a coherent obstacle avoidance and phototropic behaviour. The evolution process is carried out in a simulated envi-ronment and individuals with high performance are also tested on a physical environment with the use of Khepera robots.