EVALUATING A DDPG REINFORCEMENT LEARNING AGENT ON A BALL-AND-PLATE SYSTEM: A COMPARATIVE STUDY OF INTELLIGENT CONTROL APPROACHES
DOI:
https://doi.org/10.4314/njt.v44i2.16Keywords:
Ball and Plate, Proportional integral derivative, Model Predictive Control, Sliding Mode Control, Linear Quadratic Regulator, Deep Reinforcement LearningAbstract
This research investigates the performance of a novel deep reinforcement learning (DRL) agent in comparison with traditional intelligent control approaches for manipulating the tilt angles of ball-and-plate system. This study highlights the strengths and weaknesses of each technique through extensive experimentation and analysis of step response and trajectory tracking metrics while trailing a circular path. While the DRL agent demonstrates rapid responsiveness, it exhibits inferior trajectory tracking accuracy compared to the other methods, namely, Proportional-Integral-Derivative (PID), Model Predictive Control (MPC), Sliding Mode Control (SMC), and Linear Quadratic Regulator (LQR). These findings emphasize the importance of balancing speed and precision in control system design. Traditional methods like PID, MPC, and SMC showcase robust performance in achieving precise trajectory tracking with minimal error and overshoot, underscoring their suitability for practical applications. This comparative analysis contributes valuable insights for researchers and practitioners in control engineering, guiding the development of suitable control strategies for dynamic systems. Future research can consider hybrid control strategies that combine the strengths of traditional methods with reinforcement learning to achieve optimal tuning of the reinforcement learning agent for superior performance.
References
[1] Awtar, S., Bernard, C., Boklund, N., Master, A., Ueda, D., and Craig, K. “Mechatronic design of a ball-on-plate balancing system,” Mechatronics, vol. 12, no. 2, pp. 217–228, 2002. https://doi.org/10.1016/S0957-4158(01) 00062-9
[2] Knuplez, A., Chowdhury, A., and Svecko, R. “Modeling and control design for the ball and plate system,” in IEEE International Conference on Industrial Technology, 2003, IEEE, 2003, pp. 1064–1067. https://doi.org/ 10.1109/ICIT.2003.1290810
[3] Okafor, E., Udekwe, D., Muhammad, M. H., Ubadike, O., and Okafor, E. “Solar system maximum power point tracking evaluation using reinforcement learning”, In Proceedings of 2021 Sustainable Engineering and Industrial Technology Conference. 2021.
[4] Ham, C., and Taufiq, M. M. “Development of a ball and plate system,” in 2015 ASEE Annual Conference and Exposition, 2015, pp. 26–518. https://doi.org/10.18260/p.23857
[5] Rigatos, G., Cuccurullo, G., Busawon, K., Gao, Z., and Abbaszadeh, M. “Nonlinear optimal control of the ball and plate dynamical system,” in AIP Conference Proceedings, AIP Publishing, 2022. https://doi.org/10.1063/5.00 81624
[6] Jadlovska, A., Jajčišin, Š., and Lonščák, R. “Modelling and pid control design of nonlinear educational model ball and plate,” in 17th international conference on process control, 2009, pp. 871–874.
[7] Aphiratsakun, N., and Otaryan, N. “Ball on the plate Model based on PID tuning methods,” in 2016 13th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Tech-nology (ECTI-CON), IEEE, 2016, pp. 1–4. https://doi.org/10.1109/ECTICon.2016.7561324
[8] Núñez, D., Acosta, G., and Jiménez, J. “Control of a ball-and-plate system using a State-feedback controller,” Ingeniare: Revista Chilena de Ingenieria, vol. 28, no. 1, pp. 6–15, 2020.
[9] Elshamy, M. R., Nabil, E., Sayed, A., and Abozalam, B. “Enhancement of the Ball Balancing on the Plate using hybrid PD/Machine learning techniques,” in Journal of Physics: Conference Series, IOP Publishing, 2021, p. 012028. https://iopscience.iop.org/ article/10.1088/1742-6596/2128/1/012028
[10] Elshamy, M., Shoaib, M., Nabil, E., Sayed, A., and Abozalam, B. “Stabilization and tracking enhancement of the ball on the plate system based on Pseudo-PD controller and machine learning algorithms.,” EasyChair, 2021.
[11] Zarzycki, K., and Ławryńczuk, M. “Fast real-time model predictive control for a ball-on-plate process,” Sensors, vol. 21, no. 12, p. 3959, 2021. https://doi.org/10.3390/s21123959
[12] Umar, A., Mu’azu, M. B., Usman, A. D., Musa, U., Ajayi, O., and Yusuf, A. M. “Linear quadratic Gaussian (LQG) control design for position and trajectory tracking of the ball and plate system,” Computing and Information Systems, vol. 23, no. 1, 2019.
[13] Okafor, E., Udekwe, D., Ibrahim, Y., Bashir Mu’azu, M., and Okafor, E. G. “Heuristic and deep reinforcement learning-based PID control of trajectory tracking in a ball-and-plate system,” Journal of Information and Telecom-munication, vol. 5, no. 2, pp. 179–196, 2021. https://doi.org/10.1080/24751839.2020.1833137
[14] Oglah, A. A., and Msallam, M. M. “Real-time implementation of Fuzzy Logic Controller based on chicken swarm optimization for the ball and plate system,” International Review of Applied Sciences and Engineering, 2021. https://doi.org/10.1556/1848.2021.00360
[15] Spacek, L., Bobal, V., and Vojtesek, J. “Digital control of Ball and Plate model using LQ controller,” in 2017 21st International Conference on Process Control (PC), IEEE, 2017, pp. 36–41. https://doi.org/10.1109/PC.20 17.7976185
[16] Udekwe, D., Ajayi, O., Ubadike, O., Ter, K., and Okafor, E. “Comparing actor-critic deep reinforcement learning controllers for enhanced performance on a ball-and-plate system,” Expert Syst Appl, vol. 245, p. 123055, 2024. https://doi.org/10.1016/j.eswa.2023.123055
[17] Umar, A., and Muazu, M. B. “Position and Trajectory Tracking Control for the Ball and Plate System using Position and Trajectory Tracking Control for the Ball and Plate System using Mixed Sensitivity Problem,” vol. 6, no. October, 2018.
[18] Adetifa, A. O., Okonkwo, P. P., Muhammed, B. B., and Udekwe, D. A. “Deep reinforcement learning for aircraft longitudinal control augmentation system,” Nigerian Journal of Technology, vol. 42, no. 1, pp. 144–151, 2023. https://doi.org/10.4314/njt.v42i1.18
[19] Okafor, E. G., Udekwe, D., Ubadike, O. C., Okafor, E., Jemitola, P. O., and Abba, M. T. “Photovoltaic System MPPT Evaluation Using Classical, Meta-Heuristics, and Reinforcement Learning-Based Controllers: A Comparative Study,” Journal of Southwest Jiaotong Univer-sity, vol. 56, no. 3, 2021. https://doi.org/10.3 5741/issn.0258-2724.56.3.1
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Nigerian Journal of Technology
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The contents of the articles are the sole opinion of the author(s) and not of NIJOTECH.
NIJOTECH allows open access for distribution of the published articles in any media so long as whole (not part) of articles are distributed.
A copyright and statement of originality documents will need to be filled out clearly and signed prior to publication of an accepted article. The Copyright form can be downloaded from http://nijotech.com/downloads/COPYRIGHT%20FORM.pdf while the Statement of Originality is in http://nijotech.com/downloads/Statement%20of%20Originality.pdf
For articles that were developed from funded research, a clear acknowledgement of such support should be mentioned in the article with relevant references. Authors are expected to provide complete information on the sponsorship and intellectual property rights of the article together with all exceptions.
It is forbidden to publish the same research report in more than one journal.
How to Cite
