This paper will look at an evolutionary approach to robotics; partly at pragmatic issues, but primarily at theoretical issues associated with the evolutionary algorithms which are appropriate. Genetic Algorithms (GAs) are not suitable in their usual form for the evolution of cognitive structures, which must be in an incremental fashion. SAGA --- Species Adaptation Genetic Algorithms --- is a conceptual framework for extending GAs to variable length genotypes, where evolution allows a species of individuals to evolve from simple to more complex. In the context of species evolution the metaphor of hill-crawling as opposed to hill-climbing is introduced, and appropriate mutation rates discussed. On both pragmatic and theoretical grounds, it will be suggested that there are good reasons for using Tournament Selection in evolutionary robotics.
Download compressed postscript file