Evolving Robot Controllers for Structured Environments Through Environment Decomposition

In this paper we aim to develop a controller that allows a robot to traverse an structured environment. The approach we use is to decompose the environment into simple sub-environments that we use as basis for evolving the controller. Specifically, we decompose a narrow corridor environment into four different sub-environments and evolve controllers that generalize to traverse two larger environments composed of the sub-environments. We also study two strategies for presenting the sub-environments to the evolutionary algorithm: all sub-environments at the same time and in sequence. Results show that by using a sequence the evolutionary algorithm can find a controller that performs well in all sub-environments more consistently than when presenting all sub-environments together. We conclude that environment decomposition is an useful approach for evolving controllers for structured environments and that the order in which the decomposed sub-environments are presented in sequence impacts the performance of the evolutionary algorithm.