Evolving a metabolic subsumption architecture for cooperative control of the e-puck

Abstract

Subsumption architectures are a well-known model for behaviour-based robotic control. The global behaviour is achieved by defining a hierarchy of increasingly sophisticated behaviours. We are interested in using evolutionary algorithms to develop appropriate control architectures. We observe that the layered arrangement of behaviours in subsumption architectures are a significant obstacle to automating the development of control systems. We propose an alternative subsumption architecture inspired by the bacterial metabolism, that is more amenable to evolutionary development, in which communities of simple reactive agents combine in a stochastic process to confer appropriate behaviour on the robot. We evaluate this approach by developing a traditional and a metabolic solution to a simple control problem using a simulation of the e-puck educational robot. Additionally we show that behavioural strategies designed into the metabolic controller can also be optimised through artificial evolution.