Sliding Mode Control of a 2DOF Robot Manipulator: A Simulation Study Using Artificial Neural Networks with Minimum Parameter Learning

Background: In this paper we have developed an intelligent control law for the control of mobile manipulator robots by investigating the various techniques proposed in the literature. Thus, we have adopted a hybrid approach integrating part of classical and advanced automation in order to create an efficient control structure that can cope with a certain level of complexity. Our research logic is based on the process of keeping in mind that the control system must comply with the constraints imposed during the implementation of the control architecture. Objective: This paper aims to develop a control law in order to guarantee a certain level of performance and, more precisely, during a trajectory tracking application for mobile handling mis-sions. The developed control law guarantees robustness with respect to external disturbances and parametric uncertainties due to the modelling of the system. Methods: In this paper, a study of the basic concepts of robotics and robot modelling is presented in order to set up the dynamic model used for the elaboration of the command. A sliding-mode controller based on a radial base function neural network with minimum parameter learning is developed for the Pelican robot as a two link robot manipulator. This approach, which combines a Radial Base Function Neuronal Network (RBFNN) and a Sliding Mode Control (SMC), is presented for the tracking control of this class of systems with unknown nonlinearities. The centres and outputs weights of the RBFNN are updated via online learning in accordance with the adaptive laws, allowing the control output of the neural network to approach the equivalent control in the sliding mode in the predetermined direction. The Lyapunov function is used to develop the adaptive control algorithm based on the RBFNN model. To reduce computational load and increase real-time arm performance, an RBFNN-based on the SMC with the Minimum Parameter Learning (MPL) method is designed. Results: Neural network sliding mode control is designed to underline the effectiveness of the approach to control the manipulator. This method of control ensure the tracking trajectories. Conclusion: The results of the simulation for the manipulator arm presented demonstrates the effectiveness of the modelling strategy, the correction and the robustness of the control approach. © 2022 Bentham Science Publishers.