Cooperative Coevolution of Control for a Real Multirobot System
The potential of cooperative coevolutionary algorithms (CCEAs) as a tool for evolving control for heterogeneous multirobot teams has been shown in several previous works. The vast majority of these works have, however, been confined to simulation-based experiments. In this paper, we present one of the first demonstrations of a real multirobot system, operating outside laboratory conditions, with controllers synthesised by CCEAs. We evolve control for an aquatic multirobot system that has to perform a cooperative predator-prey pursuit task. The evolved controllers are transferred to real hardware, and their performance is assessed in a non-controlled outdoor environment. Two approaches are used to evolve control: a standard fitness-driven CCEA, and novelty-driven coevolution. We find that both approaches are able to evolve teams that transfer successfully to the real robots. Novelty-driven coevolution is able to evolve a broad range of successful team behaviours, which we test on the real multirobot system.
KeywordsCooperative coevolution Evolutionary robotics Novelty search Reality gap Heterogeneous multirobot systems
This work was supported by centre grant (to BioISI, Centre Reference: UID/MULTI/04046/2013), from FCT/MCTES/PIDDAC, Portugal, and by grants SFRH/BD/89095/2012 and UID/EEA/50008/2013.
- 1.Costa, V., Duarte, M., Rodrigues, T., Oliveira, S.M., Christensen, A.L.: Design and development of an inexpensive aquatic swarm robotics system. In: OCEANS 2016-Shanghai, pp. 1–7. IEEE Press (2016)Google Scholar
- 4.Gomes, J., Mariano, P., Christensen, A.L.: Avoiding convergence in cooperative coevolution with novelty search. In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pp. 1149–1156. IFAAMAS (2014)Google Scholar
- 5.Gomes, J., Mariano, P., Christensen, A.L.: Cooperative coevolution of morphologically heterogeneous robots. In: European Conference on Artificial Life, pp. 312–319. MIT Press (2015)Google Scholar
- 6.Gomes, J., Mariano, P., Christensen, A.L.: Devising effective novelty search algorithms: a comprehensive empirical study. In: Genetic and Evolutionary Computation Conference (GECCO), pp. 943–950. ACM Press (2015)Google Scholar
- 7.Gomes, J., Mariano, P., Christensen, A.L.: Novelty-driven cooperative coevolution. Evol. Comput. (2016, in press)Google Scholar
- 18.Potter, M.A., Meeden, L.A., Schultz, A.C.: Heterogeneity in the coevolved behaviors of mobile robots: the emergence of specialists. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 1337–1343. Morgan Kaufmann (2001)Google Scholar
- 21.Wiegand, R.P., Liles, W.C., De Jong, K.A.: Analyzing cooperative coevolution with evolutionary game theory. In: Congress on Evolutionary Computation (CEC), vol. 2, pp. 1600–1605. IEEE Press (2002)Google Scholar