ROBUST ADAPTIVE TRAJECTORY TRACKING CONTROL FOR ROBOT MANIPULATORS BASED ON ITERATIVE LEARNING CONTROL AND RBF NEURAL NETWORKS
Keywords
DOI:
https://doi.org/10.34238/tnu-jst.12923Abstract
Trajectory tracking control plays a crucial role in the performance of robot manipulators, especially in complex, nonlinear, and uncertain environments. This paper presents a robust trajectory tracking control method for robot manipulators based on an iterative learning control and radial basis function networks. The proposed approach combines a proportional-derivative-type iterative learning control law with an online radial basis function network for disturbance estimation and a switching term to enhance robustness during the early learning stage. The radial basis function network adaptively approximates unknown dynamics and external disturbances without requiring prior information, while the switching term ensures initial stability before the network converges. A Lyapunov-based analysis in the iteration domain is used to rigorously prove the convergence of both the trajectory tracking error and the estimation error. Numerical simulations on the robot manipulator were conducted to evaluate the effectiveness of the proposed method in comparison with the adaptive sliding mode controller. The results indicate that the proposed controller not only provides superior trajectory tracking performance -particularly during rapid transitions and sudden parameter variations - but also generates significantly smoother control torques.Downloads
References
C. Chen, H. Liu, and W. He, "Iterative learning control for uncertain robot manipulators with input saturation," IEEE Trans. Ind. Electron., vol. 67, no. 1, pp. 708–717, 2020.
W. He, C. Sun, and Y. Li, "Adaptive neural control of robotic manipulators with unknown dead-zone input," IEEE Trans. Cybern., vol. 52, no. 7, pp. 6751–6762, 2022.
J. Zhou and Y. Sun, “Robust adaptive neural control for robot manipulators with dead-zone input and uncertain dynamics," Neurocomputing, vol. 450, pp. 41–50, 2021.
Z. Li and H. Wang, "An improved iterative learning control scheme for robotic manipulators using PD-type learning and disturbance observer," Int. J. Control Autom. Syst., vol. 19, pp. 1317–1327, 2021.
H. Wang, Y. Chen, and D. Guo, "Adaptive iterative learning control for robot manipulator systems with non-repetitive uncertainties," IEEE Access, vol. 10, pp. 22854–22864, 2022.
Y. Zhao and W. He, "Neural network-based adaptive iterative learning control for robotic manipulators," IEEE Trans. Syst., Man, Cybern.: Syst., vol. 50, no. 12, pp. 5116–5127, 2020.
L. Gao et al., "Adaptive fuzzy iterative learning control of robotic manipulators with input saturation," IEEE Trans. Ind. Electron., vol. 70, no. 1, pp. 371–381, 2023.
P. Shi and Y. Li, "Robust learning control for robotic manipulators with uncertain kinematics and dynamics," J. Franklin Inst., vol. 357, no. 6, pp. 3512–3534, 2020.
H. Liu and W. He, "Adaptive learning control for flexible joint robots with unknown input delays and disturbances," IEEE Trans. Ind. Electron., vol. 69, no. 1, pp. 918–928, 2022.
L. Xu, X. Chen, and M. Fei, "Adaptive neural network control of robot manipulators using RBF approximation and barrier Lyapunov function," Neural Comput. Appl., vol. 33, no. 24, pp. 17821–17833, 2021.
L. Yu and X. Wang, "RBF neural networks based adaptive control for robotic manipulators with input constraints," IEEE Trans. Neural Netw. Learn. Syst., vol. 34, no. 5, pp. 2210–2222, 2023.
Y. Zhang and W. He, "RBF neural network-based adaptive control of robot manipulators with unknown input saturation," IEEE Trans. Syst., Man, Cybern.: Syst., vol. 51, no. 11, pp. 6606–6617, 2021.
W. He, C. Sun, and S. Liu, "Learning control for robotic manipulators based on recurrent neural networks," IEEE Trans. Neural Netw. Learn. Syst., vol. 31, no. 10, pp. 4021–4032, 2020.
Z. Jin and S. Xie, "Improved PD-type iterative learning control for nonlinear systems with application to robotic manipulators," Int. J. Control, vol. 95, no. 3, pp. 727–736, 2022.
Y. Pan, X. Liu, and D. Yue, "Event-triggered learning control of robot manipulators with disturbance observer," IEEE Trans. Cybern., vol. 51, no. 7, pp. 3539–3550, 2021.
F. Zhang, L. Guo, and X. Zhao, "Disturbance-observer-based robust learning control for robotic manipulators," Mechatronics, vol. 68, 2020, Art. no. 102375.
J. Ren and B. Xiao, "Adaptive neural sliding-mode control for robotic manipulators with external disturbances," IEEE Access, vol. 11, pp. 10789–10798, 2023.
C. Liang et al., "Adaptive learning control for nonlinear systems using neural networks," IEEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 1, pp. 117–128, 2022.
Z. Li and H. Wang, "Neural learning adaptive control for robotic manipulators with input delay and actuator faults," Int. J. Robust Nonlinear Control, vol. 33, no. 2, pp. 1094–1112, 2023.
B. Wu and W. He, "Learning control of robotic arms using Lyapunov–Krasovskii functionals," IEEE Trans. Syst., Man, Cybern.: Syst., vol. 51, no. 8, pp. 4982–4991, 2021.
M. Boukattaya, H. Gassara, and T. Damak, "A global time-varying sliding-mode control for the tracking problem of uncertain dynamical systems," ISA transactions, vol. 97, pp. 155–170, 2020.
D. D. Nguyen et al., "Optimal tracking control for robot manipulators with input constraint based reinforcement learning," J. Comput. Sci. Cybern., vol. 39, no. 2, pp.175–189, 2023.
D. D. Nguyen and V. T. Vu, "Adaptive synchronous sliding control for a robot manipulator based on neural networks and fuzzy logic," Int. J. Electr. Comput. Eng., vol. 14, no. 3, pp. 2377–2385, 2024.
Y. Huang, H. Liu, Z. Qiao, and D. Sun, "Adaptive sliding mode control for robotic manipulators with uncertainties and input disturbances," IEEE Trans. Ind. Electron., vol. 69, no. 2, pp. 1805–1814, 2022.
