Augmenting Scalable Communication-Based Role Allocation for a Three-Role Task

Abstract

In evolutionary robotics role allocation studies, it is common that the role assumed by each robot is strongly associated with specific local conditions, which may compromise scalability and robustness because of the dependency on those conditions. To increase scalability, communication has been proposed as a means for robots to exchange signals that represent roles. This idea was successfully applied to evolve communication-based role allocation for a two-role task, with one communication channel. However, it was necessary to reward signal differentiation in the fitness function, which is a serious limitation as it does not generalize to tasks where the number of roles is unknown a priori. We show that rewarding signal differentiation is not necessary to evolve communication-based role allocation strategies for the referred two-role task, and we improve reported scalability, while requiring less a priori knowledge. We extend the previous work to a three-role task and we propose and compare two cognitive architectures, to increase the number of communication channels, and several fitness functions to evolve scalable controllers. Our results suggest that communication might be useful to evolve role allocation strategies for increasingly complex tasks.