Automatic Creation of an Autonomous Agent: Genetic Evolution of a Neural Network Driven Robot

Abstract

The paper describes the results of the evolutionary development of a real, neural-network driven mobile robot.The evolutionary approach t o t h e development of neural controllers for autonomous agents has been successfully used by m a n y researchers, but most -if not all-studies have been carried out with computer simulations.Instead, in this research the whole evolutionary process takes places entirely on a real robot without human intervention.Although the experiments described here tackle a simple task of navigation and obstacle avoidance, we s h o w a n umber of emergent phenomena that are characteristic of autonomous agents.The neural controllers of the evolved best individuals display a full exploitation of non-linear and recurrent connections that make them more e cient than analogous man-designed agents.In order to fully understand and describe the robot behavior, we h a ve also employed quantitative ethological tools 13], and showed that the adaptation dynamics conform to predictions made for animals.