Online and Onboard Evolution of Robotic Behavior Using Finite State Machines
Published: 2009 Mai
Buchtitel: Proceedings Of The 8th International Conference On Autonomous Agents And Multiagent Systems (Aamas 2009)
Seiten: to appear
In this paper, a control system representation based on finite state machines is utilized to build an evolutionary robotic framework where evolution is performed in a swarm of simple robots in an online and onboard manner. Experiments in simulation show that the framework is capable of robustly evolving basic benchmark behaviors like collision avoidance.