A Multi-UAV Cooperative Path-Planning Method for Complex Obstacle Environments
Sensors · 19.08.2026 · 26 (16) · 5242
DOI: 10.3390/s26165242 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 19.08.2026. Verfasst von Long Wen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Power Engineering College, Naval University of Engineering, No. 717 Jiefang Road, Wuhan 430033, China. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shenzhen Science and Technology Program, Guangdong Basic and Applied Basic Research Foundation.
Abstract (Originalsprache)
Reinforcement learning techniques have been widely applied to multi-UAV cooperative path-planning tasks. However, existing multi-agent reinforcement learning methods are still affected by environmental non-stationarity, cooperation difficulties among agents, and low utilization efficiency of experience samples in complex obstacle environments. These issues often lead to slow convergence and unstable training performance. To address these problems, an Improved Experience Replay Multi-Agent Deep Deterministic Policy Gradient (IER-MADDPG) algorithm is proposed for multi-UAV cooperative path planning. First, a cooperative path-planning model is established under the Centralized Training Distributed Execution framework. Second, a dual-layer replay buffer structure consisting of a global replay buffer and a local replay buffer is designed to preserve both global cooperative information and individual experience. Third, a fusion experience sampling mechanism is introduced by combining prioritized experience replay and random uniform sampling to improve sample utilization efficiency and training stability. Finally, training experiments were conducted in environments with different obstacle configurations to evaluate the proposed method. Experimental results demonstrate that IER-MADDPG outperforms other comparison algorithms in terms of convergence speed, training stability, and path-planning performance.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Power Engineering College, Naval University of Engineering, No. 717 Jiefang Road, Wuhan 430033, China.
- School of Mechanical Engineering and Electronic Information, China University of Geosciences, No. 388 Lumo Road, Wuhan 430074, China.
- National Key Laboratory of Electromagnetic Effect and Security on Marine Equipment, China Ship Development and Design Center (CSDDC), Wuhan 430061, China.
ORCID-Profile: Long Wen
Förderung
- Shenzhen Science and Technology Program
- Guangdong Basic and Applied Basic Research Foundation
Zitieren
APA
Wen, L., Tan, H., Liu, Y., Zhao, X., Xie, S., & Zhao, B. (2026). A Multi-UAV Cooperative Path-Planning Method for Complex Obstacle Environments. Sensors, 26(16), 5242. https://doi.org/10.3390/s26165242
Vancouver
Wen L, Tan H, Liu Y, Zhao X, Xie S, Zhao B. A Multi-UAV Cooperative Path-Planning Method for Complex Obstacle Environments. Sensors. 2026;26(16):5242. doi:10.3390/s26165242
BibTeX
@article{Wen2026,
author = {Wen, Long and Tan, Hui and Liu, Yuxin and Zhao, Xinyang and Xie, Shaowang and Zhao, Bo},
title = {A Multi-UAV Cooperative Path-Planning Method for Complex Obstacle Environments},
journal = {Sensors},
year = {2026},
volume = {26},
number = {16},
pages = {5242},
doi = {10.3390/s26165242}
}
EUVIMED