Optimizing the structure of RBF neural network-based controller for Omnidirectional Mobile Robot control

Abstract

This paper proposes a method to optimize the structure of the radial basis function neural network (RBFNN) by using particle swarm optimization (PSO) algorithm. The combination of PSO and RBFNN can overcome the disadvantages of RBF neural network. The PSO algorithm is used to determine the number of hidden neurons, initial weights, center and base widths in RBF neural network. After being optimised, the RBF neural network-based controller is applied in trajectory tracking to control an Omnidirectional Mobile Robot. This is a holonomic robot that can be operated easily in small and narrow spaces, due to flexible rotational and translational movementing, simultaneously and independently. The simulation results in MATLAB Simulink show that PSO-RBF-PD Supervisory controller was better than RBF-PD Supervisory controller.