Evolutionary robotics: exploiting the full power of self-organization

Evolutionary robotics approaches are based on genetic algorithms. An initial population of different “genotypes”, each codifying the control system (and possibly the morphology) of a robot, are created randomly. Each robot is evaluated in the environment and to each robot is assigned a score (fitness) that measures its ability to perform a desired task Then, the robots that have obtained the highest fitness are allowed to reproduce (sexually or agamically) by generating copies of their genotypes with the addition of changes introduced by some genetic operators (e.g. mutations, duplication, etc.). The process is repeated for a certain number of generations until, hopefully, the desired performances are achieved. The authors discuss the implications of evolutionary robotics for other disciplines. Although they think that evolutionary robotics may be relevant for many different fields, they restrict their analysis to engineering, biology, and ethology