Spontaneous evolution of structural modularity in robot neural network controllers

Abstract

In order to evolve large robot controllers for increasingly complex tasks, fully connected neural networks are not feasible. However, manually designing sparse neural connectivity is not intuitive, and thus should be placed under evolutionary control. Here I show how spontaneous structural modularity can arise in the connectivity of evolved robot controllers if the controllers are boolean networks, and are selected to converge on point attractors that correspond to successful robot behaviors.