Abstract:A stable gait generation algorithm based on T-S type fuzzy learning net method is proposed in this paper. Reinforcement learning method is introduced into fuzzy network to learn the gain parameters. Few fuzzy rules are needed to formulate the nonlinear relation between the ZMP(zero moment point) curve and hip trajectory. The problem of multi-variables in continuous space is also simplified to search the independent action gains simultaneously. Simulation experiments on Luna biped robot prove its feasibility.
[1] Pratt J E. Exploiting Inherent Robustness and Natural Dynamics in the Control of Biped Walking Robots [D]. USA:MIT, 2000. [2] Katic D, Miomir V. Survey of intelligent control techniques for humanoid robots[J]. Journal of Intelligent and Robotic Systems, 2003,37(2):117-141. [3] Kawarnura S, Kawarnura T, Fujino D, et al. Realization of biped locomotion by motion pattern learning [J]. Journal of the Robotics Society of Japan, 1985,3(3):5-15. [4] Takanishi A, Li Q H, Kato I. Learning control of compensative trunk motion for biped walking robot based on ZMP stability criterion [A].Proceedings of the 1992 IEEE/RSJ International Conference on Intelligent Robots and Systems[C]. 1992, 1. 597-603. [5] Huang Q, Yokoik. Planning walking patterns for a biped robot[J].IEEE Transactions on Robotics and Automation, 2001,17(3):280-289. [6] Zhou C J, Jagannathan K, Myint T. Prescribed synergy methodbased hybrid intelligent gait synthesis for biped robot [A]. Proceedings of the 1999 IEEE International Conference on Robotics & Automation[C]. 1999, 2. 1384-1389.