A self-tuning trajectory tracking controller for wheeled mobile robots

Abstract

Purpose Trajectory tracking is a common problem in the field of mobile robots which has attracted a lot of attention in the past two decades. Therefore, besides the search for new controllers to achieve a better performance, improvement and optimization of existing control rules are necessary. Trajectory tracking control laws usually contain constant gains which affect greatly the robot’s performance. Design/methodology/approach In this paper, a method based on neural networks is introduced to automatically upgrade the gains of a well-known trajectory tracking controller of wheeled mobile robots. The suggested method speeds up the convergence rate of the main controller. Findings Simulations and experiments are performed to assess the ability of the suggested scheme. The obtained results show the effectiveness of the proposed method. Originality/value In this paper, a method based on neural networks is introduced to automatically upgrade the gains of a well-known trajectory tracking controller of wheeled mobile robots. The suggested method speeds up the convergence rate of the main controller.