Title: Cellular neural network trainer and template optimisation for advanced robot locomotion based on genetic algorithm

Authors: Alireza Fasih, Jean Chamberlian Chedjou, Kyandoghere Kyamakya

Addresses: Transportation Informatics Group, University of Klagenfurt, Klagenfurt, Austria. ' Transportation Informatics Group, University of Klagenfurt, Klagenfurt, Austria. ' Transportation Informatics Group, University of Klagenfurt, Klagenfurt, Austria

Abstract: A new learning algorithm for advanced robot locomotion is described in this paper. This method involves both cellular neural networks (CNN|s) technology and evolutionary algorithms. Learning is formulated as an optimisation problem. CNN Templates are derived from the genetic algorithms after an optimisation process. A template generates a specific wave on CNN that leads to the best motion of a walker robot. Details of the algorithm and several application and simulations 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.

Keywords: CNNs; cellular neural networks; walker robots; robot locomotion; GAs; genetic algorithms; robot learning; optimisation; robot walking; simulation.

DOI: 10.1504/IJISTA.2010.030188

International Journal of Intelligent Systems Technologies and Applications, 2010 Vol.8 No.1/2/3/4, pp.36 - 45

Available online: 11 Dec 2009 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article