Evolving topology and weights of specialized and non-specialized neuro-controllers for robot motion in various environments

This paper deals with the topology and weight evolution of Neuro-Controllers (NCs). It focuses on meta-problems of developing motion controllers that can operate successfully in several given motion-problems, where each of these motion problems defers by the arena and task. Here, the evolution aims to find both specialized and non-specialized controllers. The non-specialized controllers are evolved to provide a successful motion for the entire set of the given motion-problems, whereas each specialized controller is evolved to be optimal in at least one of these problems. The meta-problem is defined as a many-objective optimization problem, in which the kth objective is to maximize the motion performance in the kth motion problem. Following the problem description, a decomposition-based evolutionary algorithm, which is termed NEWS/D, is presented. This algorithm, which has recently been proposed by the authors, is specially designed to allow the topology and weight evolution of NCs under a large number of objectives. Next, the algorithm is applied to find NCs for three meta-problems, i.e., three sets of motion problems. The results of the experiments show that the obtained three sets of NCs include both specialized and non-specialized controllers. In addition, the proposed approach of many-objective topology and weight evolution of NCs is analyzed in comparison with other approaches, including three versions of decomposition-based fixed topology optimization. It is shown here that for the same number of evaluations, NEWS/D achieved better results than those of the other approaches. Finally, a topology analysis is carried out for the specialized NCs, which suggests that the solution includes multiple equivalent NCs. The numerical implications of this phenomenon are left for future work.