Substantiation of the effectiveness of unmanned aerial vehicle control for the needs of agricultural production based on the application of a neural network approach
DOI:
https://doi.org/10.31359/2311-441X-2025-27-67Keywords:
agricultural production, automated control systems, neural network, UAV trajectory, drones, trajectory prediction, neural network architecture, synthetic dataset, 3D modelingAbstract
An important vector for the development of agricultural production is the use of artificial intelligence and automated control systems in various branches of agribusiness. One of the main components of the application of automated control systems is the efficiency, simplification and safety of human labor in agricultural production in various jobs. The use of a neural network approach in the control system of various automated systems and mechanisms in various jobs makes it possible to increase their efficiency. The aim of the work is to increase the accuracy of predicting the flight trajectory of a drone by developing a trajectory prediction model based on a neural network approach. Based on a set of video materials for training a neural network, a model for predicting the flight trajectory of a UAV was developed. Using the Blender 3D modeling tool, a set of data was created based on the display of various scenarios of environmental conditions. The neural network architecture includes long-short-term memory (LSTM) blocks that are able to process sequential data, making them ideal for predicting the dynamic trajectory of a UAV.
The results show that the neural network showed better performance in real-world scenarios compared to traditional trajectory prediction methods. The integration of LSTM allowed for effective learning and generalization of temporal data, capturing complex movements and interactions with the environment. This study not only demonstrates the possibility of using neural network learning for UAV trajectory prediction, but also livestock management, automated crop harvesting and sorting, plant and soil management, etc. In addition, real-time trajectory prediction can significantly improve the efficiency and speed of decision-making. The scientific novelty of the results lies in the development and training of learning models based on the neural network approach, specifically designed for drone flight trajectory prediction. This study demonstrates the effectiveness of the proposed approach and its ability to increase the accuracy of UAV trajectory prediction.
References
1. Гарафонова О., Маргасова В. Перспективи впровадження інноваційних технологій розвитку агропромислового комплексу України. Socio-economic relations in the digital society. 2022. № 3 (45). С. 19–28. DOI: https://doi.org/10.55643/ser.3.45.2022.475.
2. Information and Communication Technology (ICT) in Agriculture: A Report to the G20 Agricultural Deputies. Rome: FAO, 2017. 57 p.
3. Болтянська Н.І., Маніта І.Ю., Подашевська О. Проблеми і перспективи розвитку інформаційних технологій в сільському господарстві. Праці Таврійського державного агротехнологічного університету імені Дмитра Моторного. 2020. Т. 20. № 4. С. 175–185. DOI: 10.31388/2078- 0877-2020-20-4-175-185.
4. Апуневич І.П. Штучний інтелект як рушій змін у сучасному сільському господарстві. «Агробіологія», 2024. № 2. С. 6-13.
5. AgroDSS: A decision support system for agriculture and farming / M. Kukar et al. Computers and Electronics in Agriculture. 2023. 161 p., P. 260-271.
6. Kumari, S., Venkatesh, V.G., Tan, F.T.C. (2023). Application of machine learning and artificial intelligence on agriculture supply chain: a comprehensive review and future research directions. Ann Oper Res. DOI: 10.1007/s10479-023-05556-3
7. Yue, J., Manocha, D., & Wang, H. Human trajectory prediction via neural social physics. Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, 2022, vol. 13694. Springer, Cham. DOI: 10.1007/978-3-031-19830-4_22.
8. Liu, Y., Yan, Q., & Alahi, A. Social NCE: Contrastive learning of socially-aware motion representations. IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 15118-15129. DOI: 10.48550/arXiv.2012.11717.
9. Bezsonov, O., Liashenko, S., Rudenko, O., Rutska, S., &Vashchenko, K, (2025) Using a deep learning network to predict flight path. Radioelectronic and Computer Systems, 2025(1), 71-84. doi: https://doi.org/10.32620/reks.2025.1.5
10. Qin, W., Tang, J., Lu, C., & Lao, S. Trajectory prediction based on long short-term memory network and Kalman filter using hurricanes as an example. Computational Geosciences, 2021, vol. 25, pp. 1005-1023. DOI: 10.1007/s10596-021-10037-2.
11. An, Y., Liu, A., Liu, H., & Geng, L. Multidimensional trajectory prediction of UAV swarms based on dynamic graph neural network. IEEE access, 2024, vol. 12, pp. 57033-57042. DOI: 10.1109/ACCESS.2024.3391374.
