Parameter tuning of CPGs for hexapod gaits based on Genetic Algorithm

In the Central Pattern Generator (CPG) inspired locomotion control, it is difficult to set appropriate weight values of oscillator network and initial values of each oscillator to generate the desired pattern with specific amplitude, frequency and phase lag. In this paper, a novel method tuning the parameters of CPGs for hexapod gaits based on Genetic Algorithm (GA) is presented. And the CPG model discussed in this work is based on Van Der Pol (VDP) equation. The process of parameter-tuning has two stages:(i) searching parameter values of single VDP oscillator to generate periodic oscillation sign with specific amplitude and frequency. (ii)searching synaptic weight values of oscillator network and initial values of each oscillator to generate specific phase lag. Two experiments have been taken in MATLAB and the results show the feasibility of the presented method in searching appropriate parameters to generate different hexapod gaits.

[1]  P. Holmes,et al.  The nature of the coupling between segmental oscillators of the lamprey spinal generator for locomotion: A mathematical model , 1982, Journal of mathematical biology.

[2]  Tamio Arai,et al.  Wave CPG model for autonomous decentralized multi-legged robot: Gait generation and walking speed control , 2006, Robotics Auton. Syst..

[3]  Chunlin Zhou,et al.  Design and Locomotion Control of a Biomimetic Underwater Vehicle With Fin Propulsion , 2012, IEEE/ASME Transactions on Mechatronics.

[4]  Jianwei Zhang,et al.  A Survey on CPG-Inspired Control Models and System Implementation , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[5]  Danwei Wang,et al.  CPG-Inspired Workspace Trajectory Generation and Adaptive Locomotion Control for Quadruped Robots , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[6]  Auke J. Ijspeert,et al.  Biorobotics: Using robots to emulate and investigate agile locomotion , 2014, Science.

[7]  Aude Billard,et al.  Biologically inspired neural controllers for motor control in a quadruped robot , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[8]  C. Pinto,et al.  Hexapod Robots : New CPG Model for Generation of Trajectories 1 , 2012 .

[9]  Balth van der Pol Jun Docts. Sc.,et al.  LXXII. The heartbeat considered as a relaxation oscillation, and an electrical model of the heart , 1928 .

[10]  Ludovic Righetti,et al.  Programmable central pattern generators: an application to biped locomotion control , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[11]  S. Amari,et al.  Characteristics of Random Nets of Analog Neuron-Like Elements , 1972, IEEE Trans. Syst. Man Cybern..

[12]  Yun Li,et al.  Genetic algorithm automated approach to the design of sliding mode control systems , 1996 .