Di Mario, Ezequiel LeonardoNavarro, InakiMartinoli, Alcherio2014-06-272014-06-272014-06-27201610.1007/978-3-319-23778-7_39https://infoscience.epfl.ch/handle/20.500.14299/104804In this paper we study the automatic synthesis of robotic controllers for the coordinated movement of multiple mobile robots. The algorithm used to learn the controllers is a noise-resistant version of Particle Swarm Optimization, which is applied in two different settings: centralized and distributed learning. In centralized learning, every robot runs the same controller and the performance is evaluated with a global metric. In the distributed learning, robots run different controllers and the performance is evaluated independently on each robot with a local metric. Our results from learning in simulation show that it is possible to learn a cooperative task in a fully distributed way employing a local metric, and we validate the simulations with real robot experiments where the best solutions from distributed and centralized learning achieve similar performances.Distributed LearningCooperative BehaviorsFlockingParticle Swarm Optimizationtext::conference output::conference proceedings::conference paper