The Benefits of Adaptive Behavior and Morphology for Cooperation

Abstract

This is a study on the role of morphology (sensor configuration) and behavioral (control system) adaptation in simulated robot teams that must accomplish cooperative tasks. The research objective was to elucidate the necessary features and computational mechanics of a method that automates the behavior-morphology design of robot teams that must accomplish cooperative tasks (tasks that cannot be optimally solved by individual robots). Results indicate that automating behavior morphology design is beneficial as task complexity increases, compared to evolving behaviors in fixed morphology teams. However, increased task complexity does not necessarily equate to the evolution of increased morphological complexity in teams.