INFORMATION TECHNOLOGY OF AUTONOMOUS NEUROFUZZY MOTION CONTROL OF THE GROUND MOBILE ROBOTICS PLATFORM

Ivan Tsmots, Vasyl Teslyuk, Yurii Opotyak, Vasyl Rabyk, Oleksandr Oliinyk

Abstract


Background. The development of ground-based mobile robotic platform (GBMRP) motion control systems requires ensuring autonomy, adaptability to dynamic environmen­tal changes, and consideration of limitations on computing resources, mass, dimensional parameters, and energy consumption. Traditional methods of GBMRP motion control, based on accurate mathematical models, are ineffective in real dynamic conditions, where it is impossible to accurately describe the state of the GBMRP and its environment. Therefore, for GBMRP motion control in such situations, the development of an appropriate information technology based on fuzzy logic and neural networks is proposed.

Materials and Methods. Information technology for autonomous neurofuzzy control of the GBMRP movement is developed based on integrated, hybrid, and problem-oriented approaches using component-oriented technology. Fuzzy logic methods will ensure the flexibility and stability of the control system in the presence of noise, measurement errors, and unpredictable environmental changes, and enable integration with neural networks to increase accuracy and speed. Neural network methods offer enhanced accuracy in navigation measurements, data recovery, and the construction of a neural-like defuzzifier, resulting in improved control signal formation.

Results and Discussion. An information technology for autonomous neurofuzzy control of the GBMRP movement has been developed, which, through the use of methods and means of collecting, storing and processing navigation data under conditions of interference and incomplete information, a combination of fuzzy logic and neuro-like structures based on the Sequential Geometric Transformations Model, has ensured adaptability and decision-making under conditions of uncertainty, and the accuracy of the formation of control signals. A fuzzy logic rule base has been developed, providing an adequate representation of expert knowledge in the control system.

Conclusion. In this work, an information technology for autonomous neurofuzzy control of the GBMRP in dynamically changing situations has been developed, based on integrated, hybrid, and problem-oriented approaches using component-oriented technology, while considering limitations on computing resources and energy consumption. 

Keywords: information technology, fuzzy logic, neural network, ground mobile robotics platform, platform motion control, defuzzification.


Full Text:

PDF

References


[1] Al Mahmud, S., Kamarulariffin, A., & Ibrahim, A. M. (2024). Advancements and challenges in mobile robot navigation: A comprehensive review of algorithms and potential for self-learning approaches. Journal of Intelligent & Robotic Systems, 110(1), 120. https://doi.org/10.1007/s10846-024-02149-5

[2] Al-Mayyahi, A., & Al-Mansoori, M. (2023). Adaptive neuro-fuzzy inference system for autonomous ground vehicle navigation. Journal of Robotics and Automation, 12(3), 45–59. https://doi.org/10.1016/j.jra.2023.03.005

[3] Antonelli, G., & Siciliano, B. (2022). Fuzzy logic-based path-following for differential drive mobile robots. IEEE Transactions on Robotics and Automation, 18(4), 564–573. https://doi.org/10.1109/TRA.2022.3145678

[4] Baturone, I., & García, J. (2023). Low-cost embedded neuro-fuzzy controller for mobile robot navigation. Robotics and Autonomous Systems, 145, 103652. https://doi.org/10.1016/j.robot.2023.103652

[5] Boubertakh, M., & Boudjema, F. (2021). Design of fuzzy controllers for obstacle avoidance and goal-seeking behaviors in mobile robots. International Journal of Intelligent Robotics and Applications, 5(2), 123–135. https://doi.org/10.1007/s41315-021-00110-5

[6] Brahmi, M., & Boukhetala, D. (2020). Path planning and localization of mobile robots using recurrent neural networks. Neural Computing and Applications, 32(7), 1955–1967. https://doi.org/10.1007/s00542-020-05583-3

[7] Demirli, E., & Khoshnejad, M. (2019). Sensor-based neuro-fuzzy controller for autonomous parallel parking of a car-like mobile robot. Journal of Intelligent & Robotic Systems, 95(2), 345–358. https://doi.org/10.1007/s10846-019-01052-3

[8] Dongshu, L., & Zhang, X. (2018). Intelligent autonomous navigation structure for a vehicle using multi-layered neural networks. Journal of Intelligent Systems, 27(1), 45–56. https://doi.org/10.1515/jisys-2017-0051

[9] Deshpande, S., & Bhosale, S. (2017). Navigation of a nonholonomic wheeled mobile robot using ANFIS controller. Procedia Computer Science, 115, 319–326. https://doi.org/10.1016/j.procs.2017.09.139

[10] Bodiansky E. V. et al. Analysis and processing of data flows by means of computational intelligence: Monograph – Lviv: Lviv Polytechnic Publishing House, 2016. – 235 pp. (In Ukrainian).

[11] Godjevac. J. (1999) Neuro-fuzzy control of a mobile robot, Proc. 1999 IEEE Inter­national Conference on Systems, Man, and Cybernetics, Tokyo, Japan, pp. 145–150.

[12] Gharajeh, M. S., Nadimi-Shahraki, M. H. and Gharajeh, M. E. (2020) Hybrid GPS-ANFIS approach for collision-free navigation of mobile robots, Robotics and Autonomous Systems, vol. 133. https://doi.org/10.1016/j.robot.2020.103669

[13] Hilali, B. (2023) Neuro-Fuzzy Combination for Reactive Mobile Robot Navigation, Artificial Intelligence Advances, vol. 3, no. 2. https://doi.org/10.52549/ijeei.v11i2.4009

[14] Al-Mahmud, H. H. and Islam, M. M. (2024) Advancements and Challenges in Mobile Robot Navigation: A Comprehensive Review,” Applied Sciences, vol. 14, no. 1, pp. 1–27. https://doi.org/10.1007/s10846-024-02149-5

[15] Dey, S. R., Hossain, A. and Rahman, F. (2025) Deep Reinforcement Learning-Based ANFIS Controller for Autonomous Navigation, IEEE Access, vol. 13, pp. 18763–18778.

[16] V. M. Khoma, “Model of sequential geometric transformations in neuro-like structures,” Bulletin of the National University “Lviv Polytechnic”,№ 879, с. 112–121, 2017. (In Ukrainian).

[17] O. V. Lutsyk, “Application of the model of successive geometric transformations in neurofuzzy control systems,” Control, Navigation and Communication Systems, №2(64), с. 38–45, 2022. (In Ukrainian).

[18] A. Mahmud et al., (2024) Real-Time Implementation of Neuro-Fuzzy Control Systems on FPGA for Mobile Robots, IEEE Transactions on Industrial Electronics, vol. 71, no. 9, pp. 9876–9887. https://doi.org/10.14569/IJACSA.2016.070136

[19] Elshamli, M., & Al-Mahmoud, A. (2016). Genetic algorithm technique for solving the path planning problem of a mobile robot in static and dynamic environments. International Journal of Advanced Robotic Systems, 13(1), 1–12. https://doi.org/10.5772/62052

[20] Elamvazuthi, I., & Rashid, R. (2015). Fuzzy-based navigation and control of a non-holonomic mobile robot. International Journal of Computer Applications, 118(24), 1–6. https://doi.org/10.5120/20809-9444

[21] Elkady, M., & Elhoseny, M. (2024). Adaptive neuro-fuzzy inference system for mobile robot navigation in dynamic environments. Computers, Materials & Continua, 70(2), 1773–1788. https://doi.org/10.32604/cmc.2024.027883

[22] Rashkevych, Yu.M., Tkachenko, R.O., Tsmots, I.G., Peleshko, D.D. Neural-like methods, algorithms and structures for real-time signal and image processing: Monograph – Lviv:2010.-130с. (In Ukrainian).

[23] García, J., & Baturone, I. (2020). Low-cost embedded neuro-fuzzy controller for mobile robot navigation. Robotics and Autonomous Systems, 144, 103652. https://doi.org/10.1016/j.robot.2020.103652

[24] Gharajeh, M. S., & Gharajeh, M. S. (2022). An intelligent approach for autonomous mobile robots path planning. Robotics and Autonomous Systems, 145, 103652. https://doi.org/10.1016/j.robot.2022.103652.

[25] Dong, L., He, Z., Song, C., & Sun, C. (2021). A review of mobile robot motion planning methods: From classical motion planning workflows to reinforcement learning-based architectures. IEEE Access, 9, 104425–104441. https://doi.org/10.1109/ACCESS.2021.3096763

[26] Liu, L., Zhang, J., & Wang, Z. (2023). Path planning techniques for mobile robots: Review and future directions. Journal of Intelligent & Robotic Systems, 101(1), 1–26. https://doi.org/10.1007/s10846-022-01615-5}




DOI: http://dx.doi.org/10.30970/eli.32.2

Refbacks

  • There are currently no refbacks.