EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Algorithm of Complete Coverage Path Planning for Unmanned Surface Vehicle Based on Reinforcement Learning

Bowen Xing, Xiao Wang, Liu Yang, Zhenchong Liu, Qingyun Wu

Journal of Marine Science and Engineering · 19.03.2023 · 11 (3) · 645

DOI: 10.3390/jmse11030645 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 19.03.2023. Verfasst von Bowen Xing und 4 weiteren Autor:innen. Die Arbeit wurde bisher 54-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanghai Science and Technology Committee (STCSM) Local Universities Capacity-building Project, Scientific Research Project of China Three Gorges Corporation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A deep reinforcement learning method to achieve complete coverage path planning for an unmanned surface vehicle (USV) is proposed. This paper firstly models the USV and the workspace required for complete coverage. Then, for the full-coverage path planning task, this paper proposes a preprocessing method for raster maps, which can effectively delete the blank areas that are impossible to cover in the raster map. In this paper, the state matrix corresponding to the preprocessed raster map is used as the input of the deep neural network. The deep Q network (DQN) is used to train the complete coverage path planning strategy of the agent. The improvement of the selection of random actions during training is first proposed. Considering the task of complete coverage path planning, this paper replaces random actions with a set of actions toward the nearest uncovered grid. To solve the problem of the slow convergence speed of the deep reinforcement learning network in full-coverage path planning, this paper proposes an improved method of deep reinforcement learning, which superimposes the final output layer with a dangerous actions matrix to reduce the risk of selection of dangerous actions of USVs during the learning process. Finally, the designed method validates via simulation examples.

Förderung

  • Shanghai Science and Technology Committee (STCSM) Local Universities Capacity-building Project
  • Scientific Research Project of China Three Gorges Corporation

Zitieren

APA

Xing, B., Wang, X., Yang, L., Liu, Z., & Wu, Q. (2023). An Algorithm of Complete Coverage Path Planning for Unmanned Surface Vehicle Based on Reinforcement Learning. Journal of Marine Science and Engineering, 11(3), 645. https://doi.org/10.3390/jmse11030645

Vancouver

Xing B, Wang X, Yang L, Liu Z, Wu Q. An Algorithm of Complete Coverage Path Planning for Unmanned Surface Vehicle Based on Reinforcement Learning. Journal of Marine Science and Engineering. 2023;11(3):645. doi:10.3390/jmse11030645

BibTeX
@article{Xing2023,
  author = {Xing, Bowen and Wang, Xiao and Yang, Liu and Liu, Zhenchong and Wu, Qingyun},
  title = {An Algorithm of Complete Coverage Path Planning for Unmanned Surface Vehicle Based on Reinforcement Learning},
  journal = {Journal of Marine Science and Engineering},
  year = {2023},
  volume = {11},
  number = {3},
  pages = {645},
  doi = {10.3390/jmse11030645}
}
Kostenlos starten →