Deep Reinforcement Learning-Based Wind Disturbance Rejection Control Strategy for UAV
Drones · 01.11.2024 · 8 (11) · 632
DOI: 10.3390/drones8110632 ↗Kurz gefasst
Fachartikel in der Zeitschrift Drones, online erschienen am 01.11.2024. Verfasst von Qun Ma und 7 weiteren Autor:innen. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of China, Science and Technology Major Project of Hubei Province.
Abstract (Originalsprache)
Unmanned aerial vehicles (UAVs) face significant challenges in maintaining stability when subjected to external wind disturbances and internal noise. This paper addresses these issues by introducing a real-time wind speed fitting algorithm and a wind field model that accounts for varying wind conditions, such as wind shear and turbulence. To improve control in such conditions, a deep reinforcement learning (DRL) strategy is developed and tested through both simulations and real-world experiments. The results indicate a 65% reduction in trajectory tracking error with the DRL controller. Additionally, a UAV built for testing exhibited enhanced stability and reduced angular deviations in wind conditions up to level 5. These findings demonstrate the effectiveness of the proposed DRL-based control strategy in increasing UAV resilience to wind disturbances.
Förderung
- Natural Science Foundation of China
- Science and Technology Major Project of Hubei Province
Zitieren
APA
Ma, Q., Wu, Y., Shoukat, M. U., Yan, Y., Wang, J., Yang, L., Yan, F., & Yan, L. (2024). Deep Reinforcement Learning-Based Wind Disturbance Rejection Control Strategy for UAV. Drones, 8(11), 632. https://doi.org/10.3390/drones8110632
Vancouver
Ma Q, Wu Y, Shoukat MU, Yan Y, Wang J, Yang L, et al. Deep Reinforcement Learning-Based Wind Disturbance Rejection Control Strategy for UAV. Drones. 2024;8(11):632. doi:10.3390/drones8110632
BibTeX
@article{Ma2024,
author = {Ma, Qun and Wu, Yibo and Shoukat, Muhammad Usman and Yan, Yukai and Wang, Jun and Yang, Long and Yan, Fuwu and Yan, Lirong},
title = {Deep Reinforcement Learning-Based Wind Disturbance Rejection Control Strategy for UAV},
journal = {Drones},
year = {2024},
volume = {8},
number = {11},
pages = {632},
doi = {10.3390/drones8110632}
}
EUVIMED