Robust Backstepping Tracking Control Using Hybrid Sliding-Mode Neural Network for a Nonholonomic Mobile Manipulator with Dual Arms

This paper presents a methodology for trajectory tracking control of a wheeled dual-arm mobile manipulator with parameter uncertainties and external load variations. Based on backstepping technique, the proposed control laws comprise two levels: kinematic and dynamic. First, the auxiliary kinematic velocity control laws for the mobile robot and the two onboard arms are separately established. Second, a robust backstepping tracking control based on hybrid sliding-mode neural networks (HSMNN) is presented to ensure the velocity tracking ability in spite of the uncertainties. The proposed robust backstepping tracking controller is actually composed of a neural network controller, a robust controller, and a proportional controller. To achieve the overall trajectory tracking goal, a neural network controller is developed to imitate an equivalent control law in the sliding-mode control, a robust controller is designed to incorporate the system dynamics into the sliding surface for guaranteeing the asymptotical stability, and the proportional controller is designed to improve the transient performance for randomly initializing neural network. All the adaptive learning algorithms for the proposed controller are derived from the Lyapunov stability theory so that the close-loop asymptotical tracking ability can be guaranteed no matter the uncertainties taken place or not. Simulation results demonstrate the feasibility as well as usefulness of the proposed control strategy in comparison with other conventional control methods.