Cellular Neural Network Trainer and Template Optimization for Advanced Robot Locomotion, Based on Genetic Algorithm

A new learning algorithm for advanced robot locomotion is described in this paper. This method involves both cellular neural networks (CNN) technology and evolutionary algorithms. Learning is formulated as an optimization problem. CNN templates are derived by genetic algorithms after an optimization process [1]. A template generates a specific wave on CNN that leads to the best motion of a walker robot. Details of the algorithm and several applications and simulation results are shown and commented. It is shown that an irregular and even a disjointed walker robot can move with the highest performance due to this method.

[1]  Luigi Fortuna,et al.  Realization of a CNN-driven cockroach-inspired robot , 2006, 2006 IEEE International Symposium on Circuits and Systems.

[2]  Luigi Fortuna,et al.  An adaptive, self-organizing dynamical system for hierarchical control of bio-inspired locomotion , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

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

[4]  P. Arena,et al.  An autonomous mini-hexapod robot controlled through a CNN-based CPG VLSI chip , 2006, 2006 10th International Workshop on Cellular Neural Networks and Their Applications.

[5]  Bharathwaj Muthuswamy,et al.  Implementing Central Pattern Generators for Bipedal Walkers using Cellular Neural Networks , 2005 .

[6]  Eleonora Bilotta,et al.  Evolving Robot's Behavior by Using CNNs , 2006, SAB.

[7]  Leon O. Chua,et al.  Genetic algorithm for CNN template learning , 1993 .

[8]  Leon O. Chua,et al.  Cellular Neural Networks and Visual Computing: Foundations and Applications , 2002 .

[9]  Sung-Bae Cho.  Evolving multiple sensory-motor controllers based on cellular neural network , 2001, Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Cat. No. 01TH8569).

[10]  Luigi Fortuna,et al.  Bio-inspired robotics: application of a CNN-based CPG VLSI chip to control an autonomous mini-hexapod robot , 2006 .

[11]  Damjan Zazula,et al.  Segmentation Of Ovarian Ultrasound Images Using Cellular Neural Networks , 2004, Int. J. Pattern Recognit. Artif. Intell..