Neural network robust H ∞ tracking control strategy for robot manipulators

• Published in: Applied mathematical modelling Vol. 34; no. 7; pp. 1823 - 1838
• Main Authors: Zuo, Yi, Wang, Yaonan, Liu, Xinzhi, Yang, Simon X., Huang, Lihong, Wu, Xiru, Wang, Zengyun
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Inc 01.07.2010; Elsevier
• Subjects: [formula omitted] control; Applied sciences; Computed torque; Computer science; control theory; systems; Control system analysis; Control system synthesis; Control theory. Systems; Drives; Exact sciences and technology; Linkage mechanisms, cams; Lyapunov stability theorem; Mechanical engineering. Machine design; Neural network; Robotics; Trajectory following problem; Trajectory following problem; H ∞ control; Neural network; Computed torque; Lyapunov stability theorem; H infinite control; Control synthesis; Tracking task; control; Robotics; N; Manipulator; Closed feedback; Robust control; Neurocontrollers; Uncertain system; Torque control; Distributed control; Tracking error; Motion control; Intelligent control; Lyapunov function
• ISSN: 0307-904X
• DOI: 10.1016/j.apm.2009.09.026

A novel neural-network-based robust H ∞ control (NNRHC) strategy is proposed for the trajectory following problem of robot manipulators. The proposed system is comprised of a computed torque controller, a variable structure slide (VSS) controller and a neural network robust controller. Based on Lyapunov stability theorem, it is shown that the proposed controller can guarantee H ∞ tracking performance of robotic system, in the sense that all variables of the closed-loop system are bounded and the effect due to the external disturbance on the tracking error can be attenuated to any pre-assigned level. The proposed approach indicates that computed torque control method is also valid for controlling robot manipulators with uncertainties as long as a compensative controller is appropriately designed. Both simulation and experimental results show the superior control performance of the proposed neural control method.