Continuous Adaptation of Robot Behaviour through Online Evolution and Neuromodulated Learning

We propose and evaluate a novel approach to the online synthesis of neural controllers for groups and swarms of autonomous robots. We combine online evolution of weights and network topology with neuromodulated learning in a completely decentralised manner. We demonstrate our method through a series of simulation-based experiments in which a group of e-puck-like robots must perform a dynamic concurrent foraging task. In this task, scattered food items periodically change their nutritive value or become poisonous. Our results show that when neuromodulated learning is employed, neural controllers are synthesised faster than by evolution alone. We demonstrate that the online evolutionary process is capable of generating controllers well adapted to the periodic task changes. We evaluate the performance both in a single robot setup and in a multirobot setup. An analysis of the evolved networks shows that they are characterised by specialised modulatory neurons that exclusively regulate online learning in the output neurons.