EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reinforcement learning for UAV flight controls: Evaluating continuous space reinforcement learning algorithms for fixed-wing UAVs

Hasan Raza Khanzada iD, Adnan Maqsood iD, Abdul Basit

PLOS One · 09.10.2025 · 20 (10) · e0334219

DOI: 10.1371/journal.pone.0334219 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 09.10.2025. Verfasst von Hasan Raza Khanzada und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Interdisciplinary Engineering and Sciences (SINES), National University of Science and Technology, Islamabad, Pakistan. Hauptthemen laut MEDLINE: Algorithms, Unmanned Aerial Devices, Reinforcement, Psychology, Aircraft. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Flight controls are experiencing a major shift with the integration of reinforcement learning (RL). Recent studies have demonstrated the potential of RL to deliver robust and precise control across diverse applications, including the flight control of fixed-wing unmanned aerial vehicles (UAVs). However, a critical gap persists in the rigorous evaluation and comparative analysis of leading continuous-space RL algorithms. This paper aims to provide a comparative analysis of RL-driven flight control systems for fixed-wing UAVs in dynamic and uncertain environments. Five prominent RL algorithms that include Deep Deterministic Policy Gradient (DDPG), Twin Delayed Deep Deterministic Policy Gradient (TD3), Proximal Policy Optimization (PPO), Trust Region Policy Optimization (TRPO) and Soft Actor-Critic (SAC) are evaluated to determine their suitability for complex UAV flight dynamics, while highlighting their relative strengths and limitations. All the RL agents are trained in a same high fidelity simulation environment to control pitch, roll and heading of the UAV under varying flight conditions. The results demonstrate that RL algorithms outperformed the classical PID controllers in terms of stability, responsiveness and robustness, especially during environmental disturbances such as wind gusts. The comparative analysis reveals that the SAC algorithm achieves convergence in 400 episodes and maintains a steady-state error below 3%, offering the best trade-off among the evaluated RL algorithms. This analysis aims to provide valuable insight for the selection of suitable RL algorithm and their practical integration into modern UAV control systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsUnmanned Aerial DevicesReinforcement, PsychologyAircraftComputer Simulation

Autor:innen und Institutionen

  • School of Interdisciplinary Engineering and Sciences (SINES), National University of Science and Technology, Islamabad, Pakistan.
  • Department of Electrical Engineering, Pakistan Institute of Engineering and Applied Sciences (PIEAS), Islamabad, Pakistan.

ORCID-Profile: Hasan Raza Khanzada, Adnan Maqsood

Zitieren

APA

Khanzada, H. R., Maqsood, A., & Basit, A. (2025). Reinforcement learning for UAV flight controls: Evaluating continuous space reinforcement learning algorithms for fixed-wing UAVs. PLOS One, 20(10), e0334219. https://doi.org/10.1371/journal.pone.0334219

Vancouver

Khanzada HR, Maqsood A, Basit A. Reinforcement learning for UAV flight controls: Evaluating continuous space reinforcement learning algorithms for fixed-wing UAVs. PLOS One. 2025;20(10):e0334219. doi:10.1371/journal.pone.0334219

BibTeX
@article{Khanzada2025,
  author = {Khanzada, Hasan Raza and Maqsood, Adnan and Basit, Abdul},
  title = {Reinforcement learning for UAV flight controls: Evaluating continuous space reinforcement learning algorithms for fixed-wing UAVs},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {10},
  pages = {e0334219},
  doi = {10.1371/journal.pone.0334219}
}
Kostenlos starten →