GA-based optimization of biped robot gait control of CPG model

As a result of the traditional artificial gait planning is a relatively rigid and slow, the lack of flexible self-organizing capacity, and the real biological differences between gait. Good use of the biological central pattern generator of the self-excited behavior have a rhythm of movement in order to adapt to a variety of coordination in complex environments, this paper, we propose a biological central pattern generator model for the core of the establishment of biped robot control system, and CPG parameter values of the parameters of genetic algorithm for high-performance distinctions, in accordance with the relationship between human movement, the establishment of the knee, hip and ankle joint movement relation equation. By simulation control mechanism based on the CPG rhythm of the biped robot motion control method is effective, bio-gait biped robot, when the realization possible.

[1]  Tamio Arai,et al.  CPG model for autonomous decentralized multi-legged robot system - generation and transition of oscillation patterns and dynamics of oscillators , 2003, Robotics Auton. Syst..

[2]  Yasuo Kuniyoshi,et al.  Three dimensional bipedal stepping motion using neural oscillators-towards humanoid motion in the real world , 1998, Proceedings. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications (Cat. No.98CH36190).

[3]  Randall D. Beer,et al.  Evolution and Analysis of Model CPGs for Walking: I. Dynamical Modules , 1999, Journal of Computational Neuroscience.

[4]  Eliano Pessa,et al.  A network model with auto-oscillating output and dynamic connections , 2004, Biological Cybernetics.

[5]  Kiyotoshi Matsuoka,et al.  Mechanisms of frequency and pattern control in the neural rhythm generators , 1987, Biological Cybernetics.

[6]  Yasuo Kuniyoshi,et al.  Three Dimensional Bipedal Stepping Motion using Neural Oscillators , 2000 .

[7]  Ralph Etienne-Cummings,et al.  A programmable array of silicon neurons for the control of legged locomotion , 2004, 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No.04CH37512).