Adaptive PD-Based Control of Robot Manipulators with Gravity Compensation and RBF Neural Networks
Keywords:
2DOF robotic manipulator; Adaptive control; Gravity compensator; Joint coupling; PD control; RBF neural network.Abstract
Robotic manipulators play an important role in automation, which requires precise control on their motions. The control of two degrees of freedom (2DOF) robotic arms is challenged by nonlinearities, joint coupling, parametric uncertainty, and external disturbances. This work proposes an efficient hybrid controller for a 2DOF robotic arm, which combines a gravity compensated proportional derivative (PD+G) controller with an adaptive radial basis function neural network (RBFNN) compensator that learn from the error signal and its derivative. The nominal robotic manipulator model along with the proposed controller, is implemented in simulation software. The proposed controller is evaluated through detailed simulations, which provide an initial validation before future experimental implementation. The validation includes overlapped step inputs to clearly reveal the coupling between joints and sinusoidal reference trajectories to examine the controller’s ability for continuous tracking. The robustness is examined by applying a step disturbance superimposed on the torque and changes in model parameters. Compared with the PD+G controller, the proposed PD+G+RBFNN control attains improved settling time for the first joint and comparable performance for the second joint, and less overshoot, while the adaptive NN effectively compensates for nonlinearities, unknown dynamics, and disturbances. Quantitative assessment of the system with controllers using several performances indices confirms the superiority of the proposed controller in all test scenarios. The highest significant improvement is achieved when applying sinusoidal tracking, with reductions of more than 90% in the performance indices as compared with the PD+G benchmark. The results show that the proposed configuration is practical, robust, and suitable for controlling nonlinear, coupled manipulators with the existence of uncertainties and disturbances.References
[1] Husainy, S. Mangave and N. Patil, A review on robotics and automation in the 21st century: Shaping the future of manufacturing, healthcare, and service sectors, Asian Review of Mechanical Engineering, 12, 2023, 41–45.
[2] Alkamachi and Y. G. K. Abboosh, Modelling and control of cable driven robotic arm using Maplesim, Advances in Electrical and Electronic Engineering, 22, 2024, 271–280.
[3] J. Wu and C. Peng, Observer‐based adaptive event‐triggered PID control for networked systems under aperiodic DoS attacks, International Journal of Robust and Nonlinear Control, 32, 2022, 2536–2550.
[4] Zhao, D. Wang and W. Xue, Beyond linear limits: Design of robust nonlinear PID control, Automatica, 173, 2025, 112075.
[5] Q. Zhou, S. Zhao, H. Li, R. Lu and C. Wu, Adaptive neural network tracking control for robotic manipulators with dead zone, IEEE Transactions on Neural Networks and Learning Systems, 30, 2019, 3611–3620.
[6] S. Ajwad, O. Iqbal and J. Iqbal, Hardware realization and PID control of multi-degree of freedom articulated robotic arm, Mehran University Research Journal of Engineering and Technology, 34, 2015, 1–12.
[7] M. S. Ahmed, A. H. M. Mary and H. H. Jasim, Robust computed torque control for uncertain robotic manipulators, Al-Khwarizmi Engineering Journal, 17, 2021, 22–28.
[8] X. Yang, Z. Zhao, Y. Li, G. Yang, J. Zhao and H. Liu, Adaptive neural network control of manipulators with uncertain kinematics and dynamics, Engineering Applications of Artificial Intelligence, 133, 2024, 107935.
[9] L. A. Soriano, E. Zamora, J. M. Vazquez-Nicolas, G. Hernández, J. A. Barraza Madrigal and D. Balderas, PD control compensation based on a cascade neural network applied to a robot manipulator, Frontiers in Neurorobotics, 14, 2020, 577749.
[10] Y. Wu, R. Huang, X. Li and S. Liu, Adaptive neural network control of uncertain robotic manipulators with external disturbance and time-varying output constraints, Neurocomputing, 323, 2019, 108–116.
[11] Q. Liu, D. Li, S. S. Ge, R. Ji, Z. Ouyang and K. P. Tee, Adaptive bias RBF neural network control for a robotic manipulator, Neurocomputing, 447, 2021, 213–223.
[12] X. Shen, K. Zhou, R. Yu and B. Wang, Design of adaptive RBFNN and computed-torque control for manipulator joint considering friction modeling, International Journal of Control, Automation and Systems, 20, 2022, 2340–2352.
[13] J. Narayan, M. Abbas, B. Patel and S. K. Dwivedy, Adaptive RBF neural network-computed torque control for a pediatric gait exoskeleton system: An experimental study, Intelligent Service Robotics, 16, 2023, 549–564.
[14] Y. Han, H. Ma, Y. Wang, D. Shi, Y. Feng, X. Li, Y. Shi, X. Ding and W. Zhang, Neural network robust control based on computed torque for lower limb exoskeleton, Chinese Journal of Mechanical Engineering, 37, 2024, 37.
[15] K. Guo and Y. Pan, Composite adaptation and learning for robot control: A survey, Annual Reviews in Control, 55, 2023, 279–290.
[16] H. Zhang, Y. Zhao, Y. Wang and L. Liu, Adaptive neural network control of robotic manipulators with input constraints and without velocity measurements, IET Control Theory & Applications, 18, 2024, 1232–1247.
[17] H. Zhang and W. Bu, H. Zhang, M. Du, G. Wu and W. Bu, PD control with RBF neural network gravity compensation for manipulator, Engineering Letters, 26, 2018, 236–244.
[18] M. W. Spong, S. Hutchinson and M. Vidyasagar, Robot Modeling and Control, New York: Wiley, 2020.
[19] J. J. Craig, Introduction to Robotics: Mechanics and Control, Pearson Education India, 2009.
[20] W. K. Sa’id, B. I. Kazem and A. M. Manaty, Hybrid controller for a single flexible link manipulator, The Journal of Engineering, 18, 2012, 1242–1254.
[21] K. H. Mahmoud, A.-N. Sharkawy and G. T. Abdel-Jaber, Development of safety method for a 3-DOF industrial robot based on recurrent neural network, Journal of Engineering and Applied Science, 70, 2023, 44.
[22] Z. Téczely and B. Kiss, Switching linear parameter varying control for a robotic manipulator, Acta IMEKO, 14, 2025, 1–8.
[23] P. Kulkarni, O. Kulkarni and J. K. Sayyad, Tuning of a robotic arm using pid controller for robotics and automation industry, 6th International Conference on Energy, Power and Environment (ICEPE), Shillong, India, 2024, 1–6.
[24] A. Tawfeeq, M. Y. Salloom and A. Alkamachi, A self-balancing platform on a mobile car, International Journal of Electrical and Computer Engineering (IJECE), 12, 2022, 5911– 5922.
[25] J. Huang, C. Yang and J. Ye, Nonlinear PD controllers with gravity compensation for robot manipulators, Cybernetics and Information Technologies, 14, 2014, 141–150.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ahmed Alkamachi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:Authors hold and retain copyright, and grant the journal right of first publication, with the work after publication simultaneously licensed under a Creative Commons Attribution 4.0 License CC BY that permits any use, reproduction and distribution of the work and article without further permission provided that the original work is properly cited.
Authors are permitted and encouraged to post their work online in institutional repositories, website and other social media before and after publication, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
