ANALYSIS OF TRADITIONAL AND NEURAL NETWORK-BASED CONTROL METHODS FOR ELECTRIC DRIVES IN ROBOTICS AND PERSPECTIVES OF HYBRID APPROACHES
Abstract
The objective of this study is to conduct a comparative analysis of traditional and neural network-based control methods for electric drives in robotics, with an emphasis on identifying their strengths and weaknesses, determining their areas of application, and assessing the prospects for the development of hybrid approaches. Effective control of electric drives is critically important for modern robotic systems, which must demonstrate high performance, reliability, and versatility in various application domains. Specifically, key challenges include high-precision trajectory tracking, energy-efficient control, robust control under uncertainties and disturbances, constraint-aware control, as well as synchronized and coordinated control of multiple electric drives. In this regard, optimizing the control of electric drives to ensure motion accuracy, energy efficiency, and adaptation to changing conditions becomes a top priority. To achieve this goal, the study systematizes and analyzes the characteristics and applications of traditional electric drive control methods, such as PID controllers, Kalman filters, sliding mode control, and model predictive control. It also examines key neural network-based approaches to electric drive control, including feedforward neural networks, recurrent neural networks, radial basis functions, neuro-fuzzy systems, and reinforcement learning. A comparative analysis of these methods is conducted to identify their advantages and limitations based on key parameters such as trajectory tracking accuracy, robustness to disturbances and uncertainties, adaptability to changing operating conditions, and computational complexity. Additionally, the study investigates and assesses the prospects for hybrid electric drive control methods that combine the reliability and control quality of traditional methods in linear and structured environments with the flexibility and adaptability of neural network-based methods in complex and dynamic robotic systems. The study’s key findings indicate that traditional electric drive control methods, such as PID controllers and sliding mode control, remain effective and preferable in linear and well-defined systems due to their simplicity and reliability. At the same time, neural network-based approaches demonstrate significant advantages in controlling complex nonlinear systems, as well as in uncertain conditions requiring adaptation to changing environments. Special attention is given to hybrid control methods, which integrate the strengths of both traditional and neural network-based approaches. These methods are regarded as the most promising and advanced direction, enabling the development of intelligent and robust electric drive control systems capable of operating efficiently in complex and dynamic environments.
References
1. Shahid M., Jin W., Abbasi M., Husain A., Munir H., Hassan M., Flah A., Souissi A.S.E., and Alghamdi T.A.H. Model predictive control for energy efficient AC motor drives: An overview, IET Electric Power Applications, 2024, No. 18, pp. 1894-1920.
2. Tinoco V., Silva M., Neves Dos Santos F., Morais R., and Moura Oliveira P. A review of advanced controller methodologies for robotic manipulators, International Journal of Dynamics and Control, 2025, No. 13.
3. Joo D., and Yeom K. Improved Hybrid Trajectory Tracking Algorithm for a 3-link Manipulator Using Artificial Neural Network and Kalman Filter, International Journal of Mechanical Engineering and Ro-botics Research, 2021, pp. 60-66.
4. Niu F., Sun K., Huang S., Hu Y., Dong L., and Fang Y. A Review on Multi-motor Synchronous Control Methods, IEEE Transactions on Transportation Electrification, 2022, No. PP, pp. 1-1.
5. Gul S., Zergeroglu E., Tatlicioglu E., and Kilinc M.V. Desired model compensation-based position con-strained control of robotic manipulators, Robotica, 2021, No. 40, pp. 1-15.
6. Zhang X., Hu H., Wang H., and Wang Z. Overview of position synchronous control technology for multi-motor system, Systems Science & Control Engineering, 2024, No. 12.
7. Ariss J., Rabat S. A comparison between a traditional PID controller and an Artificial Neural Network controller in manipulating a robotic arm (En jämförelse mellan en traditionell PIDstyrenhet och en Artifi-ciell Neural Nätverksstyrenhet för att styra en robotarm), TRITA-EECS-EX, 2019. Studenтuppsats (Ex-amensarbete), 29 p.
8. Wu Y., Huang R., Li X., and Liu S. Adaptive neural network control of uncertain robotic manipulators with external disturbance and time-varying output constraints, Neurocomputing, 2018, No. 323.
9. Frolov V.Ya., Yusef B. Modelirovanie i nelineynoe upravlenie negolonomnym avtomobilepodobnym mobil'nym robotom, otslezhivayushchim traektoriyu [Modeling and nonlinear control of a nonholonomic car-like mobile robot tracking a trajectory], Izvestiya Tul'skogo gosudarstvennogo universiteta. Tekhnicheskie nauki [Bulletin of Tula State University. Engineering sciences], 2024,
No. 2, pp. 381-388. doi: 10.24412/2071-6168-2024-2-381-382.
10. Qiao L., Zhao M., Wu C., Ge T., Fan R., and Zhang W. Adaptive PID control of robotic manipulators without equality/inequality constraints on control gains, International Journal of Robust and Nonlinear Control, 2021, No. 32.
11. Mustafa M.M., Hamarash I., Crane C.D. Adaptive-Sliding Mode Trajectory Control of Robot Manipu-lators with Uncertainties, Zanco Journal of Pure and Applied Sciences, 2020, No. 32 (4), pp. 22-29.
12. Qin M., Dian S., Guo B., Tao X., & Zhao T. Fractional-order SMC controller for mobile robot trajectory tracking under actuator fault, Systems Science & Control Engineering, 2022, 10, pp. 312-324.
13. Yigit S., & Sezgin A. Trajectory Tracking via Backstepping Controller with PID or SMC for Mobile Robots, Sakarya University Journal of Science, 2023, 27 (1), pp. 120-134.
14. Limon D., and Alamo T. Tracking Model Predictive Control, Encyclopedia of Systems and Control / ed. Baillieul, John and Samad, Tariq. London: Springer London, 2013, pp. 1-12.
15. Holzmann P., Pfefferkorn M., Peters J., Findeisen R. Learning Energy-Efficient Trajectory Planning for Robotic Manipulators Using Bayesian Optimization, Mater. Evropeyskoy konferentsii po upravleniyu (European Control Conference (ECC)), Stokgol'm, Shvetsiya. 2024 [Proceedings of the European Con-trol Conference (ECC), Stockholm, Sweden. 2024], pp. 1374-1379.
16. Pizá R., Carbonell R., Casanova V., Cuenca Á., and Salt Llobregat J.J. Nonuniform Dual-Rate Extend-ed Kalman-Filter-Based Sensor Fusion for Path-Following Control of a Holonomic Mobile Robot with Four Mecanum Wheels, Appl. Sci., 2022, No. 12, 3560.
17. Kuang С., and Zheng Х. Space Trajectory Planning of Electric Robot Based on Unscented Kalman Fil-ter, Jordan Journal of Mechanical & Industrial Engineering, 2021, No. 15 (1), pp. 29-38.
18. Kim D., Kim S-H., Kim T., Kang B., Lee M., Park W., Ku S., Kim D., Kwon J., Lee H., Bae J., Park Y-L., Cho K-J., and Jo S. Review of machine learning methods in soft robotics, PLOS ONE, 2021, No. 16, pp. e0246102.
19. Li Z., and Li S. Model-based recurrent neural network for redundancy resolution of manipulator with remote centre of motion constraints, International Journal of Systems Science, 2022, No. 53, pp. 1-14.
20. Molina-Leal A., Gómez-Espinosa A., Escobedo Cabello J., Cuan-Urquizo E., and Cruz-Ramirez S.R. Trajectory Planning for a Mobile Robot in a Dynamic Environment Using an LSTM Neural Network, Applied Sciences, 2021, No. 11, pp. 10689.
21. Patel R., Zeinali M., and Passi K. Deep Learning-based Robot Control using Recurrent Neural Net-works (LSTM; GRU) and Adaptive Sliding Mode Control.
22. Wang H., Zhou X., and Tian Y. Robust adaptive fault‐tolerant control using RBF‐based neural network for a rigid‐flexible robotic system with unknown control direction, International Journal of Robust and Nonlinear Control, 2021, No. 32.
23. Recalde L.F., Varela J., Guevara B.S., Andaluz V., and Gandolfo D. Adaptive NMPC-RBF with Appli-cation to Manipulator Robots, 2023 9th International Conference on Control, Decision and Information Technologies (CoDIT), 2023, pp. 2475-2482.
24. Hasan S.K. Radial basis function‐based exoskeleton robot controller development, IET Cyber-Systems and Robotics, 2022, No. 4, pp. 228-250.
25. Zhao M., Wang Q., Wang Y., and Dong Q. Multi-Motor Cooperative Control Strategy for Speed Syn-chronous Control of Construction Platform, Electronics, 2022, No. 11, pp. 4162.
26. Yilmaz B., Tatlicioglu E., Savran A., and Alci M. Self-Adjusting Fuzzy Logic Based Control of Robot Manipulators In Task Space, IEEE Transactions on Industrial Electronics, 2021, No. PP, pp. 1-1.
27. Al-Mallah M., Ali M., and Al-Khawaldeh M. Obstacles Avoidance for Mobile Robot Using Type-2 Fuzzy Logic Controller, Robotics, 2022, No. 11, pp. 130.
28. Elguea-Aguinaco Í., Serrano Muñoz A., Chrysostomou D., Inziarte-Hidalgo I., Bøgh S., and Arana-Arexolaleiba N. A review on reinforcement learning for contact-rich robotic manipulation tasks, Robotics and Computer-Integrated Manufacturing, 2023, No. 81, pp. 102517.
29. Lobbezoo A., Qian Y., and Kwon H-J. Reinforcement Learning for Pick and Place Operations in Robot-ics: A Survey, Robotics, 2021, No. 10, pp. 105.
30. Liu R., Nageotte F., Zanne P., De Mathelin M., and Dresp B. Deep Reinforcement Learning for the Control of Robotic Manipulation: A Focussed Mini-Review, Robotics, 2021, No. 10, pp. 22.
