Evolving Robust Robot Controllers for Corridor Following using Genetic Programming

Designing robots and robot controllers is a highly complex and often expensive task. However, genetic programming provides an automated design strategy to evolve complex controllers based on evolution in nature. We show that, even with limited computational resources, genetic programming is able to evolve efficient robot controllers for corridor following in a simulation environment. Therefore, a mixed and gradual form of layered learning is used, resulting in very robust and efficient controllers. Furthermore, the controller is successfully applied to real environments as well.