Abstract
An autonomous robot controller is generally designed by using an artificial neural network (ANN) in Evolutionary Robotics. It has been found that the topology of an ANN must be important for the improving evolvability, but the systematic design method has not been known so far. In this paper, we assume that the hidden layer is acquired in the form of a small world network in the hidden layer by Topology and Weight Evolving Artificial Neural Networks (TWEANN). The generalization capability of EANN is examined by the cooperative package pushing problems.
