Abstract:A location/decision network is presented for multi rover coordination. Fuzzy logic and reinforcement learning are combined in behavior decision for rovers. Experiment results prove the effectiveness and correctness of the method.
[1] 王巍,梁斌,夏玉华,等.月球漫游车关键技术初探[J].机器人,2003,1(3):280-284. [2] Schwartz A.A reinforcement learning method for maximizing undiscounted rewards[A].Proceedings of the Tenth International Conference on Machine Learning[C].Amherst,MA:Morgan Kanfmann Publishers,1993.298-305. [3] Whitley D,Dominic S,Das R,et al.Genetic reinforcement learning for neurocontrol problems[J].Machine Learning,1993,13(4):259-284 [4] Piggott P,Sattar A.Reinforcement learning of iterative behavior with multiple sensors[J].Journal of Applied Intelligence,1994,4(2):381-365. [5] Kaelbling L P.Associative reinforcement learning:function in K-DNF[J].Machine Learning,1994,15(2):279-298. [6] Tesauro G J.Temporal difference learning and TD-Gammon[J].Communications of the ACM,1995,38(3):58-68.