NARA Discovery
Article Details
← Back to Search Results
Journal Article

Task-Heterogeneous Formation Planning and Control for Unmanned Surface Vehicles Based on Hybrid Deep Reinforcement Learning

Yawen Zhang; Wenkui Li; Chenyang Shan; Haoyu Bu; Bing Han
Journal of Marine Science and Engineering · Vol. 14, Issue 10 · pp. 959 · 2026

Abstract

To address the control coupling challenges arising from task heterogeneity of unmanned surface vehicle (USV) formation, a distributed hybrid deep reinforcement learning (HDRL) framework is proposed. The framework decomposes the formation task into two subtasks: leader path planning using the single-agent deep reinforcement learning (SADRL) algorithm and follower formation tracking using the multi-agent deep reinforcement learning (MADRL) algorithm. By embedding the physical constraints of the real Otter USV into the training loop, the policy network outputs are mapped to propeller revolutions that conform to its dynamic characteristics. To optimize control performance, a dynamic gating mechanism triggered by formation position error is developed to mitigate multi-objective interference through temporal task scheduling. Concurrently, a mirror mapping mechanism leveraging the physical symmetry of the formation is designed to achieve policy sharing and data augmentation. Furthermore, the desired velocity calculated based on rigid-body kinematics is used to achieve kinematic-compensated formation tracking. The simulation results indicate that, compared to the SADRL algorithm, the planning success rate of HDRL is improved by 44.59%. Furthermore, compared to the MADRL algorithm, the integrated tracking performance is enhanced by 21.79–39.64%.

Bibliographic Information

JournalJournal of Marine Science and Engineering
PublisherMDPI
Publication Date2026-05-21
Publication Year2026
Volume14
Issue10
Pages959
Document TypeJournal Article
eISSN2077-1312
DOI10.3390/jmse14100959
SubjectMarine science; oceanography; marine engineering; coastal science; marine environment

Access Information

NARA Access CoverageOA / free full text
Journal Homepagehttps://www.mdpi.com/journal/jmse
Publisher PageOpen Publisher Page
This article is openly available from the publisher.