Application of Machine Learning for Adaptive Trajectory Control of UAVs Under Uncertainty
- Autores: Ermilov A.S.1, Saltykova O.A.1
-
Afiliações:
- RUDN University
- Edição: Volume 26, Nº 1 (2025)
- Páginas: 7-16
- Seção: Articles
- URL: https://journals.rcsi.science/2312-8143/article/view/327617
- DOI: https://doi.org/10.22363/2312-8143-2025-26-1-7-16
- EDN: https://elibrary.ru/JNLPXG
- ID: 327617
Citar
Texto integral
Resumo
The article explores the potential of applying machine learning (ML) for adaptive trajectory control of unmanned aerial vehicles (UAVs) under uncertainty. The concepts of ML algorithms and the classification of UAVs by purpose, size, and weight are examined. To analyze control methods, theoretical approaches such as ensemble learning, neural networks, and probabilistic models are applied, enabling real-time adaptation of flight trajectories. Additionally, mathematical models are presented and illustrated with formulas describing the dynamics of interaction between the control system, external disturbances, and control inputs. Parameters such as system adaptability, trajectory correction accuracy, and stability under challenging conditions are studied to assess the accuracy and efficiency of the proposed algorithms. The study also investigates the impact of computational power limitations on the real-time performance of algorithms. The integration of data from various sensors is considered crucial for improving the accuracy and reliability of the control system. Special attention is given to the practical application of ML for environmental change prediction and flight trajectory optimization. Examples of real-world ML algorithm implementations include successful developments by Russian and foreign companies, demonstrating high levels of autonomy and adaptive control. The results show that ML significantly enhances UAV autonomy and safety, ensuring reliable trajectory corrections even under uncertain conditions. Further research could focus on developing collective control for UAV groups and improving real-time ML integration. This would expand UAV functionality, improve efficiency, and reduce resource consumption.
Palavras-chave
Sobre autores
Alexander Ermilov
RUDN University
Email: eemilov-sasha@yandex.ru
ORCID ID: 0009-0007-4549-172X
Código SPIN: 8696-5057
Postgraduate student of the Department of Mechanics and Control Processes, Academy of Engineering
6 Miklukho-Maklaya St, Moscow, 117198, Russian FederationOlga Saltykova
RUDN University
Autor responsável pela correspondência
Email: saltykova-oa@rudn.ru
ORCID ID: 0000-0002-3880-6662
Código SPIN: 3969-6707
PhD in Physical and Mathematical Sciences, Associate Professor of the Department of Mechanics and Control Processes, Academy of Engineering
6 Miklukho-Maklaya St, Moscow, 117198, Russian FederationBibliografia
- Obukhov AD, Nazarova AO. A control method based on computer vision and machine learning technologies for adaptive systems. Мechatronics, Automation, Control. 2023;24(1):14-23. (In Russ.) https://doi.org/10.17587/mau.24.14-23 EDN: YZTOPE
- Davletov AR. Modern machine learning methods and OCR technology for document processing automation. Bulletin of Science. 2023;10(67):677-697. (In Russ.) https://doi.org/10.24412/2712-8849-2023-1067-676-698 EDN: OZQMOC
- Andrievsky BR, Popov AM, Mikhailov VA, Popov FA. Application of artificial intelligence methods for UAV flight control. Aerospace Engineering and Technology.2023;1(2):72-107. (In Russ.) EDN: CLGVYM
- Alam MM, Moh S. Joint Trajectory Control, Frequency Allocation, and Routing for UAV Swarm Networks:A Multi-Agent Deep Reinforcement Learning Approach. IEEE Transactions on Mobile Computing. 2024;23(12). https://doi.org/10.1109/TMC.2024.3403890
- Davletov AR. The main difficulties in integrating machine learning into commercial operation. Innovation & Investment. 2023;(10):335-339. (In Russ.) EDN: UBCPOX
- Xiao Y. Machine learning-based design of a linear self-resistant attitude control system for UAV string level. Applied Mathematics and Nonlinear Sciences. 2024;9(1):1-24. https://doi.org/10.2478/amns.2023.2.01320 EDN: MTBMZX
- Perrusquía A, Guo W, Fraser B, Wei Z. Uncovering drone intentions using control physics informed machine learning. Communications Engineering. 2024;3(1):1-26. https://doi.org/10.21203/rs.3.rs-3127372/v1
- Kazakov LN, Kubyshkin EP, Paley DE. Construction of an adaptive motion control system optimal information exchange scheme for a group of unmanned aerial vehicle. Modeling and Analysis of Information Systems. 2023;30(1):16-26. (In Russ.) https://doi.org/10.18255/1818-1015-2023-1-16-26 EDN: TOCUAE
- Tomakova RA, Pilist SA, Brezhneva AN, Gorbachev IN, Zaikin YO. Method and algorithm of autonomous flight trajectory planning of an unmanned aerial vehicle when monitoring the fire situation in order to detect the source of ignition early. Proceedings of the Southwest State University. Series: Control, Computer Engineering, Infor-mation Science. Medical Instruments Engineering. 2023;13(1):93-110. (In Russ.) https://doi.org/10.21869/2223-1536-2023-13-1-93-110 EDN: COTWER
- Sembiring J, Sasongko RA, Bastian EI, Raditya BA, Limansubroto RE. A Deep Learning Approach for Trajectory Control of Tilt-Rotor UAV. Aerospace. 2024;11(1):96. https://doi.org/10.3390/aerospace11010096 EDN: CDJAEF
- Tang J, Xie N, Li K, Liang Ya, Chen X. Trajectory Tracking Control for Fixed-Wing UAV Based on DDPG. Journal of Aerospace Engineering. 2024;37(3):04024012. https://doi.org/10.1061/JAEEEZ.ASENG-528 EDN: JHDCBC
- Kulida EL, Lebedev VG. Problems in the application of machine learning methods in aviation. Management of the Development of Large-Scale Systems (MLSD’2023). Proceedings of the XVI International Conference, Moscow, September 26-28, 2023. Moscow: V.A. Trapeznikov Institute of Management Problems of the Russian Academy of Sciences, 2023;1315-1321. (In Russ.) https://doi.org/10.25728/mlsd.2023.1315 EDN: RHPWHH
- Malygin DS. Microservice architecture in cloud systems: risks and application opportunities in 2024-2030. Modeling, optimization and information technology. 2024;12(2):29. (In Russ.) https://doi.org/10.26102/2310-6018/2024.45.2.029 EDN: JGOZIT
- Han X, Zhao X, Xu X, Mei C, Xing W, Wang X. Trajectory tracking control for underactuated autonomous vehicles via adaptive dynamic programming. Journal of the Franklin Institute. 2024;361(1):474-488. https://doi.org/10.1016/j.jfranklin.2023.12.003 EDN: HEEQAV
- Fagundes-Junior LA, de Carvalho KB, Ferreira RS, Brandão AS. Machine Learning for Unmanned Aerial Vehicles Navigation: An Overview. SN Computer Science. 2024;5(2):1-26. https://doi.org/10.1007/s42979-023-02592-5 EDN: MXAHWC
- Lezhankin BV, Erokhin VV, Malisov NP. Control of the flight path of an unmanned aerial vehicle with different configurations of navigation information sources. Crede Experto: Transport, Society, Education, Language. 2024;(1):113-127. (In Russ.) https://doi.org/10.51955/2312-1327_2024_1_113 EDN: NSRDTA
- Haque E, Hasan K, Ahmed I, Alam MS, Islam T. Towards an Interpretable AI Framework for Advanced Classification of Unmanned Aerial Vehicles (UAVs). 2024 IEEE 21st Consumer Communications & Networking Conference (CCNC). IEEE, 2024. p. 644-645. https://doi.org/10.1109/CCNC51664.2024.10454862
- Castro GGR, Berger GS, Cantieri A, Teixeira MAS, Lima J, Pereira AI, Pinto MF. Adaptive path planning for fusing rapidly exploring random trees and deep reinforce-ment learning in an agriculture dynamic environment UAVs. Agriculture. 2023;13(2):354. https://doi.org/10.3390/agriculture13020354 EDN: KEROLZ
- Artemov A. Programming languages in data engi-neering: overview, trends and practical application. Innovation Science. 2023;10-2:9-13. EDN: LLGVKL
- Artyomov AA. Datacontract in analytical systems: basic principles, practical benefits and implementation methods. Bulletin of Science. 2023;12(69):800-812. (In Russ.) EDN: HUTTTS
- Sahani SK, Sah AK, Jha A, Sahani K. Analytical Frameworks: Differential Equations in Aerospace Engi-neering. ALSYSTECH Journal of Education Technology. 2024;2(1):13-30. https://doi.org/10.58578/alsystech.v2i1.2267 EDN: NWEDOP
Arquivos suplementares
