Reinforcement learning with fuzzy evaluative feedback for a biped robot

Proposes a fuzzy reinforcement learning algorithm for biped gait synthesis. It is based on a modified GARIC (generalized approximate reasoning for intelligent control) architecture that can accept fuzzy evaluative feedback rather than a numerical one. The proposed gait synthesizer forms the initial gait from intuitive balancing knowledge, and it is then trained by the fuzzy reinforcement learning algorithm that uses a fuzzy critical signal to evaluate the degree of success for the biped dynamic walking by means of the zero moment point. The performance and applicability of the proposed method are illustrated through biped simulation.

[1]  M. Vukobratovic,et al.  Biped Locomotion , 1990 .

[2]  Atsuo Takanishi,et al.  Learning of robot biped walking with the cooperation of a human , 1993, Proceedings of 1993 2nd IEEE International Workshop on Robot and Human Communication.

[3]  Changjiu Zhou,et al.  Prescribed synergy method-based hybrid intelligent gait synthesis for biped robot , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[4]  Shuuji Kajita,et al.  Adaptive Gait Control of a Biped Robot Based on Realtime Sensing of the Ground Profile , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[5]  Jerry E. Pratt,et al.  Intuitive control of a planar bipedal walking robot , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).

[6]  W.T. Miller.  Real-time neural network control of a biped walking robot , 1994, IEEE Control Systems.

[7]  Yuan F. Zheng,et al.  Reinforcement learning for a biped robot to climb sloping surfaces , 1997, J. Field Robotics.

[8]  Toru Yamaguchi,et al.  Realization of a high speed biped using modern control theory , 1984 .

[9]  Yoshihiko Nakamura,et al.  Making feasible walking motion of humanoid robots from human motion capture data , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[10]  T. A. McMahon,et al.  Mechanics of Locomotion , 1984, Muscles, Reflexes, and Locomotion.

[11]  Hamid R. Berenji,et al.  Learning and tuning fuzzy logic controllers through reinforcements , 1992, IEEE Trans. Neural Networks.

[12]  Ching-Long Shih,et al.  Gait Synthesis for a biped robot , 1997, Robotica.

[13]  Hyung Suck Cho,et al.  A sensor-based navigation for a mobile robot using fuzzy logic and reinforcement learning , 1995, IEEE Trans. Syst. Man Cybern..

[14]  Shuuji Kajita,et al.  Adaptive Gait Control of a Biped Robot Based on Realtime Sensing of the Ground Profile , 1997, Auton. Robots.

[15]  Da Ruan,et al.  Integration of linguistic and numerical information for biped control , 1999, Robotics Auton. Syst..

[16]  Changjiu Zhou.  Neuro-fuzzy gait synthesis with reinforcement learning for a biped walking robot , 2000, Soft Comput..

[17]  Chin-Teng Lin,et al.  Adaptive fuzzy command acquisition with reinforcement learning , 1998, IEEE Trans. Fuzzy Syst..