EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Path planning for UAVs in complex terrain based on the PGD model: Algorithmic improvements combining feature extraction and reinforcement learning

Liangshuai Liu iD, Xiaofeng Li, Lingming Meng, Yuntao Zhao, Yaya Lv

PLOS One · 03.02.2026 · 21 (2) · e0340394

DOI: 10.1371/journal.pone.0340394 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 03.02.2026. Verfasst von Liangshuai Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: State Grid Hebei Electric Power Research Institute, Shijiazhuang, Hebei, China. Hauptthemen laut MEDLINE: Algorithms, Unmanned Aerial Devices, Models, Theoretical. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes the PGD model for UAV path planning in complex terrain, addressing key challenges such as high-dimensional state processing, blind path exploration, and poor cross-scene adaptability. The PGD model integrates Transformer, GAN, and DDPG, forming a “compression-generation-optimization" closed-loop system. The Transformer module compresses high-dimensional terrain data, alleviating training bottlenecks, while the GAN module generates high-quality candidate paths, reducing ineffective exploration. DDPG then optimizes the path planning strategy efficiently. Experimental results demonstrate the superior performance of PGD on the UAVDT (suburban) and AirSim (canyon) datasets. In terms of path length ( P l ), PGD achieves 20.0m/22.0m, compared to baseline models such as PPO-DRL (23.8m) and Soft Actor-Critic (24.0m). PGD also outperforms in collision rate ( C r ) with 2.5%/3.0% and computational efficiency ( T c ) with 13.5s/16.0s, respectively. The PGD model shows significant improvements in path planning efficiency and adaptability, particularly in high-complexity terrains. Compared to traditional models, PGD’s multi-module synergy enhances feature correlation and physical path constraints, offering a novel framework for intelligent planning in complex environments. Future work will focus on enhancing model adaptability to extreme weather and multi-agent collaborative scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsUnmanned Aerial DevicesModels, TheoreticalReinforcement Machine Learning

Autor:innen und Institutionen

  • State Grid Hebei Electric Power Research Institute, Shijiazhuang, Hebei, China.

ORCID-Profile: Liangshuai Liu

Zitieren

APA

Liu, L., Li, X., Meng, L., Zhao, Y., & Lv, Y. (2026). Path planning for UAVs in complex terrain based on the PGD model: Algorithmic improvements combining feature extraction and reinforcement learning. PLOS One, 21(2), e0340394. https://doi.org/10.1371/journal.pone.0340394

Vancouver

Liu L, Li X, Meng L, Zhao Y, Lv Y. Path planning for UAVs in complex terrain based on the PGD model: Algorithmic improvements combining feature extraction and reinforcement learning. PLOS One. 2026;21(2):e0340394. doi:10.1371/journal.pone.0340394

BibTeX
@article{Liu2026,
  author = {Liu, Liangshuai and Li, Xiaofeng and Meng, Lingming and Zhao, Yuntao and Lv, Yaya},
  title = {Path planning for UAVs in complex terrain based on the PGD model: Algorithmic improvements combining feature extraction and reinforcement learning},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {2},
  pages = {e0340394},
  doi = {10.1371/journal.pone.0340394}
}
Kostenlos starten →