Hexapod locomotion control through a CNN based decentralized system

In this paper the decentralized locomotion control of a bio-inspired hexapod robot is realized by using cellular neural networks (CNNs). This approach is inspired by the model of decentralized locomotion control in the stick insect, where local influences, based on the leg status, revealed by contact sensors, coordinates the CNN cells devoted to control each of the legs. To prove the suitability of the approach, simulations of the control system when applied to a simplified dynamic hexapod model are presented. The good results obtained open the way to the realization of the control on the hexapod robot.

[1]  Jeffrey Dean,et al.  Artificial neural nets for controlling a 6-legged walking system , 1993 .

[2]  P. Arena,et al.  Reaction-diffusion CNN algorithms to generate and control artificial locomotion , 1999 .

[3]  Thomas Kindermann,et al.  Walknet--a biologically inspired network to control six-legged walking , 1998, Neural Networks.

[4]  Luigi Fortuna,et al.  Multi-template approach to artificial locomotion control , 2001, ISCAS 2001. The 2001 IEEE International Symposium on Circuits and Systems (Cat. No.01CH37196).

[5]  loannis Andreopoulos,et al.  A hybrid image compression algorithm based on fractal coding and wavelet transform , 2000, 2000 IEEE International Symposium on Circuits and Systems. Emerging Technologies for the 21st Century. Proceedings (IEEE Cat No.00CH36353).

[6]  Luigi Fortuna,et al.  A cellular nonlinear approach to decentralized locomotion control of the stick insect , 2002, 2002 IEEE International Symposium on Circuits and Systems. Proceedings (Cat. No.02CH37353).

[7]  Martin Buehler,et al.  Modeling and Analysis of a Spatial Compliant Hexapod , 2002 .

[8]  Daniel E. Koditschek,et al.  Design, modeling and preliminary control of a compliant hexapod robot , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).