| Abstract |
One of the grand challenges in self-configurable robotics is to enable robots to change their configuration, autonomously, and in parallel, depending on changes in the environment. We investigate –in simulation– if this is possible through evolutionary algorithms (EA). To this end, we implement a nonconventional on-line, on-board EA that works inside the robots, adapting their controllers to a given environment on-the-fly. This adaptive robot swarm is then exposed to changing circumstances that require that robots aggregate into “organisms” or disaggregate into swarm mode again to improve their fitness. The experimental results clearly demonstrate that this EA is capable of adapting the system in real time, without human intervention. |