The University of Sussex

Co-evolutionary design: implications for evolutionary robotics

Seth G. Bullock

Genetic algorithms (GAs) typically work on static fitness landscapes. In contrast, natural evolution works on fitness landscapes that change over evolutionary time as a result of (amongst other things) co-evolution. The attractions of co-evolutionary design techniques are discussed. and attempts to utilise co-evolution in the use of GAs as design tools are reviewed, before the implications of natural predator-prey co-evolution are considered. Utilising strict definitions of true and diffuse co-evolution provided by Janzen (1980), a distinction is drawn between two styles of evolutionary niche, Predator and Parasite. The former niche is robust with respect to environmental change and features systems that have had to solve evolutionary problems in ways that reveal general purpose design principles, whilst the nature of the latter is such that, despite being fragile and unsatisfactory in these respects, it is nevertheless evolutionarily successful. It is contested that if co-evolutionary design is to provide systems that solve problems in ways that reveal general purpose design principles, i.e. to provide robust styles of solution, true co-evolution must be abandoned in favour of diffuse co-evolutionary design regimes.

Download compressed postscript file