Cooperative coevolution of morphologically heterogeneous robots

Abstract

Morphologically heterogeneous multirobot teams have shown significant potential in many applications. While cooperative coevolutionary algorithms can be used for synthesising controllers for heterogeneous multirobot systems, they have been almost exclusively applied to morphologically homogeneous systems. In this paper, we investigate if and how cooperative coevolutionary algorithms can be used to evolve behavioural control for a morphologically heterogeneous multirobot system. Our experiments rely on a simulated task, where a ground robot with a simple sensor-actuator configuration must cooperate tightly with a more complex aerial robot to find and collect items in the environment. We first show how differences in the number and complexity of skills each robot has to learn can impair the effectiveness of cooperative coevolution. We then show how coevolution’s effectiveness can be improved using incremental evolution or novelty-driven coevolution. Despite its limitations, we show that coevolution is a viable approach for synthesising control for morphologically heterogeneous systems.