EUVIMEDEUVIMED entdecken
Crossref

Research on Collision Avoidance Algorithm of Unmanned Surface Vehicle Based on Deep Reinforcement Learning

Jiawei Xia, Xufang Zhu, Zhikun Liu, Yasong Luo, Zhaodong Wu, Qiuhan Wu

IEEE Sensors Journal · 01.06.2023 · 23 (11) · 11262-11273

DOI: 10.1109/jsen.2022.3222575 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 01.06.2023. Verfasst von Jiawei Xia und 5 weiteren Autor:innen. Die Arbeit wurde bisher 60-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: Natural Science Foundation of Hubei Province of China, China Postdoctoral Science Foundation Funded Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To solve the problem of active collision avoidance for unmanned surface vehicles (USVs) in a complex maritime environment, a method of deep reinforcement learning (DRL) based on proximal policy optimization (PPO) is proposed. To master the collision avoidance policy by self-learning, the mathematical model of USV, dynamic obstacle generation model, and reward mechanism were established. Using the relative position between the obstacle and USV and the information of the closest point of approach (CPA), high-dimensional state features including the collision track layer and collision threat layer were constructed. On this basis, combined with low-dimensional states such as navigation state and path error, a deep convolutional neural network (CNN) structure fused in multifeature and multiscale was designed. The proposed DRL network was trained through repeated collision avoidance simulations in random environments. Simulation results reveal that the proposed algorithm can output effective decisions in complex scenarios and avoid dynamic obstacles quickly and safely.

Förderung

  • Natural Science Foundation of Hubei Province of China
  • China Postdoctoral Science Foundation Funded Project

Zitieren

APA

Xia, J., Zhu, X., Liu, Z., Luo, Y., Wu, Z., & Wu, Q. (2023). Research on Collision Avoidance Algorithm of Unmanned Surface Vehicle Based on Deep Reinforcement Learning. IEEE Sensors Journal, 23(11), 11262-11273. https://doi.org/10.1109/jsen.2022.3222575

Vancouver

Xia J, Zhu X, Liu Z, Luo Y, Wu Z, Wu Q. Research on Collision Avoidance Algorithm of Unmanned Surface Vehicle Based on Deep Reinforcement Learning. IEEE Sensors Journal. 2023;23(11):11262-11273. doi:10.1109/jsen.2022.3222575

BibTeX
@article{Xia2023,
  author = {Xia, Jiawei and Zhu, Xufang and Liu, Zhikun and Luo, Yasong and Wu, Zhaodong and Wu, Qiuhan},
  title = {Research on Collision Avoidance Algorithm of Unmanned Surface Vehicle Based on Deep Reinforcement Learning},
  journal = {IEEE Sensors Journal},
  year = {2023},
  volume = {23},
  number = {11},
  pages = {11262--11273},
  doi = {10.1109/jsen.2022.3222575}
}
Kostenlos starten →