FRACTAL FITNESS LANDSCAPE AND LOSS OF ROBUSTNESS IN EVOLUTIONARY ROBOT NAVIGATION

An autonomous robot ''Khepera'' was simulated with a sensory-motor mod el, which evolves in the genetic algorithm (GA) framework, with the fi tness evaluation in terms of the navigation performance in a maze cour se. The sensory-motor model is a developed neural network decoded from a graph-represented chromosome, which is evolved in the GA process wi th several genetic operators. It was found that the fitness landscape is very rugged when it is observed at the starting point of the course . A hypothesis for this ruggedness is proposed, and is supported by th e measurement of fractal dimension. It is also observed that the perfo rmance is sometimes plagued by ''Loss of Robustness,'' after the robot makes major evolutionary jumps. Here, the robustness is quantitativel y defined as a ratio of the averaged fitness of the evolved robot navi gating in perturbed environments over the fitness of the evolved robot in the referenced environment. Possible explanation of robustness los s is the over-adaptation occurred in the environment where the evoluti on was taken place. Testing some other possibilities for this loss of robustness, many simulation experiments were conducted which smooth ou t the discrete factors in the model and environment. It was found that smoothing the discrete factors does not solve the loss of robustness. An effective method for maintaining the robustness is the use of aver aged fitness over different navigation conditions. The evolved models in the simulated environment were tested by down-loading the models in to the real Khepera robot. It is demonstrated that the tendency of fit ness values observed in the simulation were adequately regenerated.