Multi-Underwater Target Interception Strategy Based on Deep Reinforcement Learning

In the context of multiple autonomous undersea vehicles(AUVs) executing underwater target interception missions, AUVs are required to make precise decisions based on both enemy and partner information, navigating the dual challenges of competition and cooperation. Most existing research typically fo...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenhao GAN, Yunfei PENG, Lei QIAO
Format: Article
Language:zho
Published: Science Press (China) 2025-04-01
Series:水下无人系统学报
Subjects:
Online Access:https://sxwrxtxb.xml-journal.net/cn/article/doi/10.11993/j.issn.2096-3920.2025-0004
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849428773263376384
author Wenhao GAN
Yunfei PENG
Lei QIAO
author_facet Wenhao GAN
Yunfei PENG
Lei QIAO
author_sort Wenhao GAN
collection DOAJ
description In the context of multiple autonomous undersea vehicles(AUVs) executing underwater target interception missions, AUVs are required to make precise decisions based on both enemy and partner information, navigating the dual challenges of competition and cooperation. Most existing research typically focuses on single-target interception in simple environments and lacks a detailed exploration of collaborative mechanisms for multi-target interception mechanisms in complex environments. Therefore, this paper proposed a multi-agent deep reinforcement learning framework for AUVs to learn interception strategies in environments with complex obstacles and time-vary ocean currents, with a focus on cooperation in many-to-many game scenarios. First, a hierarchical maneuvering framework was introduced to improve the decision-making ability of AUVs through a three-layer loop structure. Next, the multi-agent proximal policy optimization algorithm was used to construct a scalable state and action space and design a compound reward function, enhancing interception efficiency and cooperation of AUVs. Finally, a population expansion–curriculum learning approach was incorporated within a centralized training and distributed execution architecture to help AUVs master generalizable cooperation strategies. Training results show rapid convergence and high success rates of the proposed interception strategies. The simulation experiments show that the trained AUVs can use the same set of models in multiple population configurations to effectively intercept multiple intruding targets through cooperation while avoiding obstacles.
format Article
id doaj-art-903888ff60e64aeebc12f5ccb1ce99af
institution Kabale University
issn 2096-3920
language zho
publishDate 2025-04-01
publisher Science Press (China)
record_format Article
series 水下无人系统学报
spelling doaj-art-903888ff60e64aeebc12f5ccb1ce99af2025-08-20T03:28:34ZzhoScience Press (China)水下无人系统学报2096-39202025-04-0133232533210.11993/j.issn.2096-3920.2025-00042025-0004Multi-Underwater Target Interception Strategy Based on Deep Reinforcement LearningWenhao GAN0Yunfei PENG1Lei QIAO2School of Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaSchool of Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaSchool of Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaIn the context of multiple autonomous undersea vehicles(AUVs) executing underwater target interception missions, AUVs are required to make precise decisions based on both enemy and partner information, navigating the dual challenges of competition and cooperation. Most existing research typically focuses on single-target interception in simple environments and lacks a detailed exploration of collaborative mechanisms for multi-target interception mechanisms in complex environments. Therefore, this paper proposed a multi-agent deep reinforcement learning framework for AUVs to learn interception strategies in environments with complex obstacles and time-vary ocean currents, with a focus on cooperation in many-to-many game scenarios. First, a hierarchical maneuvering framework was introduced to improve the decision-making ability of AUVs through a three-layer loop structure. Next, the multi-agent proximal policy optimization algorithm was used to construct a scalable state and action space and design a compound reward function, enhancing interception efficiency and cooperation of AUVs. Finally, a population expansion–curriculum learning approach was incorporated within a centralized training and distributed execution architecture to help AUVs master generalizable cooperation strategies. Training results show rapid convergence and high success rates of the proposed interception strategies. The simulation experiments show that the trained AUVs can use the same set of models in multiple population configurations to effectively intercept multiple intruding targets through cooperation while avoiding obstacles.https://sxwrxtxb.xml-journal.net/cn/article/doi/10.11993/j.issn.2096-3920.2025-0004autonomous undersea vehiclemulti-agentreinforcement learningtarget interceptionintelligent decision-making
spellingShingle Wenhao GAN
Yunfei PENG
Lei QIAO
Multi-Underwater Target Interception Strategy Based on Deep Reinforcement Learning
水下无人系统学报
autonomous undersea vehicle
multi-agent
reinforcement learning
target interception
intelligent decision-making
title Multi-Underwater Target Interception Strategy Based on Deep Reinforcement Learning
title_full Multi-Underwater Target Interception Strategy Based on Deep Reinforcement Learning
title_fullStr Multi-Underwater Target Interception Strategy Based on Deep Reinforcement Learning
title_full_unstemmed Multi-Underwater Target Interception Strategy Based on Deep Reinforcement Learning
title_short Multi-Underwater Target Interception Strategy Based on Deep Reinforcement Learning
title_sort multi underwater target interception strategy based on deep reinforcement learning
topic autonomous undersea vehicle
multi-agent
reinforcement learning
target interception
intelligent decision-making
url https://sxwrxtxb.xml-journal.net/cn/article/doi/10.11993/j.issn.2096-3920.2025-0004
work_keys_str_mv AT wenhaogan multiunderwatertargetinterceptionstrategybasedondeepreinforcementlearning
AT yunfeipeng multiunderwatertargetinterceptionstrategybasedondeepreinforcementlearning
AT leiqiao multiunderwatertargetinterceptionstrategybasedondeepreinforcementlearning