Genetic programming approach to the construction of a neural network for control of a walking robot

This paper describes the staged evolution of a complex motor pattern generator (MPG) for the control of a walking robot. The MPG is composed of a network of neurons with weights determined by Genetic Algorithm (GA) optimization. Staged evolution is used to improve the convergence rate of the algorithm. First, an oscilla-tor for the individual leg movements is evolved. Then, a network of these oscillators is evolved to coordinate the movements of the diierent legs. By introducing a staged set of manageable challenges, the algorithm's performance is improved. These techniques may be applicable to other complex or ill-posed control problems in robot control.