Considerations in the application of evolution to the generation of robot controllers

This paper is concerned with different aspects of the use of evolution for the successful generation of real robot Artificial Neural Network (ANN) con trollers. Several parameters of an evolutionary/genetic algorithm (GA) and the way they influence the evolution of ANN behavioral controllers for real robots have been contemplated. These parameters include the way the initia l populations are distributed, how the individuals are evaluated, the imple mentation of race schemes, etc. A batch of experiments on the evolution of three types of behaviors with different population sizes have been carried out in order to ascertain their effect on the evolution of the controllers and their validity in real implementations. The results provide a guide to the design of evolutionary algorithms for generating ANN based robot contro llers, especially when, due to computational constraints, the populations t o be used are small with respect to the complexity of the problem to be sol ved. The problem of transferring the controllers evolved in simulated envir onments to the real systems operating in real environments are also conside red and we present results of this transference to reality with a robot whi ch has few and extremely noisy sensors. (C) 2001 Elsevier Science Inc. All rights reserved.