One of the advantages of evolutionary robotics over other approaches in embodied cognitive science would be its parallel population search. Due to the population search, it takes a long time to evaluate all robot in a real environment. Thus, such techniques as to shorten the time are required for real robots to evolve in a real environment. This paper proposes to use simply coded evolutionary artificial neural networks for mobile robot control to make genetic search space as small as possible and investigates the performance of them using simulated and real robots. Two types of genetic algorithm (GA) are employed, one is the standard GA and the other is an extended GA, to achieve higher final fitnesses. The results suggest the benefits of the proposed method.
Stability of the particle swarm optimization algorithm is analyzed without any simplifying assumptions made in the previous works. To evaluate the convergence speed of the algorithm, the decay rate is introduced, and a method for finding the largest lower bound of the decay rate is presented. The proposed method is based on linear matrix inequality techniques, and therefore is carried out efficiently by using convex optimization tools. Numerical examples are given to show that the analysis method is reasonable and effective to select the parameters in the algorithm.