EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimization of Adaptive Observation Strategies for Multi-AUVs in Complex Marine Environments Using Deep Reinforcement Learning

Jingjing Zhang, Weidong Zhou, Xiong Deng, Shuo Yang, Chunwang Yang, Hongliang Yin

Journal of Marine Science and Engineering · 26.04.2025 · 13 (5) · 865

DOI: 10.3390/jmse13050865 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 26.04.2025. Verfasst von Jingjing Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSFC, NSF of Heilongjiang Province, China, Key Laboratory of Marine Environmental Information Technology (MEIT).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper explores the application of Deep Reinforcement Learning (DRL) to optimize adaptive observation strategies for multi-AUV systems in complex marine environments. Traditional algorithms struggle with the strong coupling between environmental information and observation modeling, making it challenging to derive optimal strategies. To address this, we designed a DRL framework based on the Dueling Double Deep Q-Network (D3QN), enabling AUVs to interact directly with the environment for more efficient 3D dynamic ocean observation. However, traditional D3QN faces slow convergence and weak action–decision correlation in partially observable, dynamic marine settings. To overcome these challenges, we integrate a Gated Recurrent Unit (GRU) into the D3QN, improving state-space prediction and accelerating reward convergence. This enhancement allows AUVs to optimize observations, leverage ocean currents, and navigate obstacles while minimizing energy consumption. Experimental results demonstrate that the proposed approach excels in safety, energy efficiency, and observation effectiveness. Additionally, experiments with three, five, and seven AUVs reveal that while increasing platform numbers enhances predictive accuracy, the benefits diminish with additional units.

Förderung

  • NSFC
  • NSF of Heilongjiang Province, China
  • Key Laboratory of Marine Environmental Information Technology (MEIT)

Zitieren

APA

Zhang, J., Zhou, W., Deng, X., Yang, S., Yang, C., & Yin, H. (2025). Optimization of Adaptive Observation Strategies for Multi-AUVs in Complex Marine Environments Using Deep Reinforcement Learning. Journal of Marine Science and Engineering, 13(5), 865. https://doi.org/10.3390/jmse13050865

Vancouver

Zhang J, Zhou W, Deng X, Yang S, Yang C, Yin H. Optimization of Adaptive Observation Strategies for Multi-AUVs in Complex Marine Environments Using Deep Reinforcement Learning. Journal of Marine Science and Engineering. 2025;13(5):865. doi:10.3390/jmse13050865

BibTeX
@article{Zhang2025,
  author = {Zhang, Jingjing and Zhou, Weidong and Deng, Xiong and Yang, Shuo and Yang, Chunwang and Yin, Hongliang},
  title = {Optimization of Adaptive Observation Strategies for Multi-AUVs in Complex Marine Environments Using Deep Reinforcement Learning},
  journal = {Journal of Marine Science and Engineering},
  year = {2025},
  volume = {13},
  number = {5},
  pages = {865},
  doi = {10.3390/jmse13050865}
}
Kostenlos starten →