Evolving and Optimizing Braitenberg Vehicles by Means of Evolution Strategies

This paper presents a practical application of the evolution strategy to the evolution and optimization of Braitenberg vehicles. Braitenberg vehicles are a special class of autonomous agents. Autonomous agents are embodied systems that behave in the real world without any human control. One major goal of research on autonomous agents is to study intelligence as the result of a system environment interaction, rather than understanding intelligence on a computational level. Braitenberg vehicles are controlled by a number of parameters, which are mostly determined by hand in a trial and error process. This paper shows that a simple evolution strategy evolves Braitenberg vehicles very efficiently. Other research has used genetic algorithms for very similar tasks. A comparison of both approaches shows that the evolution strategy approach is much faster; the evolution strategy approach takes about one and a half hours, whereas the genetic algorithm approach takes more than two and a half day..