论文信息 - A cellular nonlinear approach to decentralized locomotion control of the stick insect

A cellular nonlinear approach to decentralized locomotion control of the stick insect

In this paper a new approach to decentralized locomotion control of bio-inspired hexapod robots is presented. This approach is inspired by the model of decentralized locomotion control in the stick insect introduced by Cruse, where local influences, based on the leg status, revealed by contact sensors, coordinate the leg controllers. Second order nonlinear systems are used to realize the neuron-like dynamics of the leg controllers. The suitability of the approach has been shown by using cellular nonlinear networks to implement the leg controllers.

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

[2] 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).

[3] P. Arena,et al. Cellular neural networks : chaos, complexity and VLSI processing , 1999 .

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

[5] H. Cruse,et al. Simulation of Complex Movements Using Artificial Neural Networks , 1998, Zeitschrift fur Naturforschung. C, Journal of biosciences.

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