Title: Learning of fuzzy-behaviours using Particle Swarm Optimisation in behaviour-based mobile robot
Authors: Andi Adriansyah, Shamsudin H.M. Amin
Addresses: Centre of Artificial Intelligence and Robotics (CAIRO), Faculty of Electrical Engineering, Universiti Teknologi Malaysia, Skudai, 81310 Johor Bahru, Malaysia. ' Centre of Artificial Intelligence and Robotics (CAIRO), Faculty of Electrical Engineering, Universiti Teknologi Malaysia, Skudai, 81310 Johor Bahru, Malaysia
Abstract: Behaviour-based mobile robots should have an ideal controller to generate perfect behaviour action. A schema to overcome these problems is provided, known as Fuzzy Behaviour-based robot. However, tuning fuzzy parameters is not a simple effort. This paper presents a technique to tune automatically fuzzy Rule Bases and fuzzy Membership Functions (MF) by Particle Swarm Optimisation (PSO), named as Particle Swarm Fuzzy Controller (PSFC). The behaviours are controlled by PSFC to generate individual command action. Later, a Context-Dependent Blending (CDB) based on meta-fuzzy rules coordinates the commands to produce final control action. A Sigmoid Decreasing Inertia Weight has been proposed for a good balancing of global and local searches for obtaining good convergence speed and best accuracy of PSO algorithm. The algorithm is validated using parameters of MagellanPro mobile robot and tested by simulation using MATLAB/SIMULINK. Simulation results show that the proposed model offers hopeful advantages and has improved performance.
Keywords: behaviour-based robots; fuzzy behaviour; fuzzy systems; particle swarm fuzzy controllers; PSFC; particle swarm optimisation; PSO; mobile robots; robot behaviour; fuzzy control; robot simulation.
International Journal of Intelligent Systems Technologies and Applications, 2008 Vol.5 No.1/2, pp.49 - 67
Published online: 05 May 2008 *Full-text access for editors Access for subscribers Purchase this article Comment on this article