Evolution of Signalling in a Group of Robots Controlled by Dynamic Neural Networks

Communication is a point of central importance in swarms of robots. This paper describes a set of simulations in which artificial evolution is used as a means to engineer robot neuro-controllers capable of guiding groups of robots in a categorisation task by producing appropriate actions. In spite of the absence of explicit selective pressure (coded into the fitness function) which favours signalling over nonsignalling groups, communicative behaviour emerges. Post-evaluation analyses illustrate the adaptive function of the evolved signals and show that they are tightly linked to the behavioural repertoire of the agents. Finally, our approach for developping controllers is validated by successfully porting one evolved controller on real robots.