Adaptive neural network control of a robotic manipulator with unknown backlash-like hysteresis

• Published in: IET control theory & applications Vol. 11; no. 4; pp. 567 - 575
• Main Authors: He, Wei, Ofosu Amoateng, David, Yang, Chenguang, Gong, Dawei
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 24.02.2017
• Subjects: adaptive control; adaptive neural network controller; backlash‐like hysteresis; Computer simulation; control nonlinearities; Controllers; friction; full state feedback control; high gain observer; hyperbolic tangent activation function; Hysteresis; hysteresis nonlinearity; Manipulators; Neural networks; neurocontrollers; Nonlinear dynamics; observers; output feedback control; radial basis function; radial basis function networks; Research Article; Robot arms; robot dynamics; robotic manipulator; Robotics; state feedback; manipulators; adaptive control; high gain observer; friction; hysteresis; robot dynamics; robotic manipulator; full state feedback control; radial basis function; adaptive neural network controller; neurocontrollers; output feedback control; control nonlinearities; radial basis function networks; hysteresis nonlinearity; state feedback; backlash-like hysteresis; hyperbolic tangent activation function; observers
• ISSN: 1751-8644; 1751-8652
• DOI: 10.1049/iet-cta.2016.1058

This study proposes an adaptive neural network controller for a 3-DOF robotic manipulator that is subject to backlash-like hysteresis and friction. Two neural networks are used to approximate the dynamics and the hysteresis non-linearity. A neural network, which utilises a radial basis function approximates the robot's dynamics. The other neural network, which employs a hyperbolic tangent activation function, is used to approximate the unknown backlash-like hysteresis. The authors also consider two cases: full state and output feedback control. For output feedback, where system states are unknown, a high gain observer is employed to estimate the states. The proposed controllers ensure the boundedness of the control signals. Simulations are also performed to show the effectiveness of the controllers.