A New Method for Simultaneous Evolution of Robot Behaviors based on Multiobjective Evolution

This paper proposes a new method for simultaneous acquisition of different robot behaviors. The proposed method is based on multiobjective evolutionary algorithm, where each behavior is considered as separate objective function. Based on the Pareto optimal set of neural controllers the user can select the most appropriate based on his requirements. We considered evolution of a neural controller for the Cyber Rodent robot that has to complete simultaneously two different tasks: (1) protecting another moving robot by trying to keep a fixed short distance and (2) keeping a sufficient energy level by capturing the battery packs distributed in the environment. Results show a good performance of proposed method