A Genetic Regulatory Network-Inspired Real-Time Controller for a Group of Underwater Robots

Abstract

A decentralised real-time controller for a group of robots is presented, the design of which is inspired by biological genetic regulatory networks. A genetic algorithm (GA) is used to automatically evolve controllers for specific tasks. Results of initial experiments are presented and analysed, which demonstrate that it is possible to successfully evolve the controllers to achieve a simple clustering task. Performance is robust under a variety of parameter choices for the GA and controller.