Research on Unmanned Surface Vehicle Trajectory Prediction Based on the SAC-LSTM Algorithm

Xiaopeng Gao; Xiaohong Liu; Mingjin Xu

doi:10.1007/978-981-95-7664-7_16

Research on Unmanned Surface Vehicle Trajectory Prediction Based on the SAC-LSTM Algorithm

Xiaopeng Gao
, Xiaohong Liu
, Mingjin Xu^*

^*Corresponding author for this work

Naval University of Engineering Wuhan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Unmanned Surface Vehicles (USVs) are widely used in marine exploration, security, and autonomous navigation, where trajectory prediction plays a critical role in decision-making. This study proposes a prediction framework that combines a high-fidelity ship dynamics model with a Soft Actor-Critic (SAC) algorithm to optimize a Long Short-Term Memory (LSTM) network. The dynamics model includes first-order response delay and stochastic wind-wave disturbances to simulate realistic data. SAC adaptively tunes key LSTM hyperparameters, improving optimization efficiency and enhancing generalization under complex sea conditions. Experimental results show that the SAC-optimized LSTM outperforms manually tuned models, highlighting the potential of integrating deep reinforcement learning with sequence modeling for USV navigation.

Original language	English
Title of host publication	Proceedings of 5th 2025 International Conference on Autonomous Unmanned Systems, ICAUS - Volume 4
Editors	Shaorong Xie, Yifeng Niu, Wenxing Fu, Yi Qu
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	169-182
Number of pages	14
ISBN (Print)	9789819576630
DOIs	https://doi.org/10.1007/978-981-95-7664-7_16
State	Published - 2026
Externally published	Yes
Event	5th International Conference on Autonomous Unmanned Systems, ICAUS 2025 - Shanghai, China Duration: 17 Oct 2025 → 19 Oct 2025

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	1577 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	5th International Conference on Autonomous Unmanned Systems, ICAUS 2025
Country/Territory	China
City	Shanghai
Period	17/10/25 → 19/10/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 14 Life Below Water

Keywords

High-Fidelity Modeling
LSTM
SAC
Trajectory Prediction
USV

Access to Document

10.1007/978-981-95-7664-7_16

Cite this

Gao, X., Liu, X., & Xu, M. (2026). Research on Unmanned Surface Vehicle Trajectory Prediction Based on the SAC-LSTM Algorithm. In S. Xie, Y. Niu, W. Fu, & Y. Qu (Eds.), Proceedings of 5th 2025 International Conference on Autonomous Unmanned Systems, ICAUS - Volume 4 (pp. 169-182). (Lecture Notes in Electrical Engineering; Vol. 1577 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-95-7664-7_16

Gao, Xiaopeng ; Liu, Xiaohong ; Xu, Mingjin. / Research on Unmanned Surface Vehicle Trajectory Prediction Based on the SAC-LSTM Algorithm. Proceedings of 5th 2025 International Conference on Autonomous Unmanned Systems, ICAUS - Volume 4. editor / Shaorong Xie ; Yifeng Niu ; Wenxing Fu ; Yi Qu. Springer Science and Business Media Deutschland GmbH, 2026. pp. 169-182 (Lecture Notes in Electrical Engineering).

@inproceedings{5e89993643484472976b9b0e22a3323b,

title = "Research on Unmanned Surface Vehicle Trajectory Prediction Based on the SAC-LSTM Algorithm",

abstract = "Unmanned Surface Vehicles (USVs) are widely used in marine exploration, security, and autonomous navigation, where trajectory prediction plays a critical role in decision-making. This study proposes a prediction framework that combines a high-fidelity ship dynamics model with a Soft Actor-Critic (SAC) algorithm to optimize a Long Short-Term Memory (LSTM) network. The dynamics model includes first-order response delay and stochastic wind-wave disturbances to simulate realistic data. SAC adaptively tunes key LSTM hyperparameters, improving optimization efficiency and enhancing generalization under complex sea conditions. Experimental results show that the SAC-optimized LSTM outperforms manually tuned models, highlighting the potential of integrating deep reinforcement learning with sequence modeling for USV navigation.",

keywords = "High-Fidelity Modeling, LSTM, SAC, Trajectory Prediction, USV",

author = "Xiaopeng Gao and Xiaohong Liu and Mingjin Xu",

note = "Publisher Copyright: {\textcopyright} Beijing HIWING Scientific and Technological Information Institute 2026.; 5th International Conference on Autonomous Unmanned Systems, ICAUS 2025 ; Conference date: 17-10-2025 Through 19-10-2025",

year = "2026",

doi = "10.1007/978-981-95-7664-7\_16",

language = "英语",

isbn = "9789819576630",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "169--182",

editor = "Shaorong Xie and Yifeng Niu and Wenxing Fu and Yi Qu",

booktitle = "Proceedings of 5th 2025 International Conference on Autonomous Unmanned Systems, ICAUS - Volume 4",

address = "德国",

}

Gao, X, Liu, X & Xu, M 2026, Research on Unmanned Surface Vehicle Trajectory Prediction Based on the SAC-LSTM Algorithm. in S Xie, Y Niu, W Fu & Y Qu (eds), Proceedings of 5th 2025 International Conference on Autonomous Unmanned Systems, ICAUS - Volume 4. Lecture Notes in Electrical Engineering, vol. 1577 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 169-182, 5th International Conference on Autonomous Unmanned Systems, ICAUS 2025, Shanghai, China, 17/10/25. https://doi.org/10.1007/978-981-95-7664-7_16

Research on Unmanned Surface Vehicle Trajectory Prediction Based on the SAC-LSTM Algorithm. / Gao, Xiaopeng; Liu, Xiaohong; Xu, Mingjin.
Proceedings of 5th 2025 International Conference on Autonomous Unmanned Systems, ICAUS - Volume 4. ed. / Shaorong Xie; Yifeng Niu; Wenxing Fu; Yi Qu. Springer Science and Business Media Deutschland GmbH, 2026. p. 169-182 (Lecture Notes in Electrical Engineering; Vol. 1577 LNEE).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Research on Unmanned Surface Vehicle Trajectory Prediction Based on the SAC-LSTM Algorithm

AU - Gao, Xiaopeng

AU - Liu, Xiaohong

AU - Xu, Mingjin

N1 - Publisher Copyright: © Beijing HIWING Scientific and Technological Information Institute 2026.

PY - 2026

Y1 - 2026

N2 - Unmanned Surface Vehicles (USVs) are widely used in marine exploration, security, and autonomous navigation, where trajectory prediction plays a critical role in decision-making. This study proposes a prediction framework that combines a high-fidelity ship dynamics model with a Soft Actor-Critic (SAC) algorithm to optimize a Long Short-Term Memory (LSTM) network. The dynamics model includes first-order response delay and stochastic wind-wave disturbances to simulate realistic data. SAC adaptively tunes key LSTM hyperparameters, improving optimization efficiency and enhancing generalization under complex sea conditions. Experimental results show that the SAC-optimized LSTM outperforms manually tuned models, highlighting the potential of integrating deep reinforcement learning with sequence modeling for USV navigation.

AB - Unmanned Surface Vehicles (USVs) are widely used in marine exploration, security, and autonomous navigation, where trajectory prediction plays a critical role in decision-making. This study proposes a prediction framework that combines a high-fidelity ship dynamics model with a Soft Actor-Critic (SAC) algorithm to optimize a Long Short-Term Memory (LSTM) network. The dynamics model includes first-order response delay and stochastic wind-wave disturbances to simulate realistic data. SAC adaptively tunes key LSTM hyperparameters, improving optimization efficiency and enhancing generalization under complex sea conditions. Experimental results show that the SAC-optimized LSTM outperforms manually tuned models, highlighting the potential of integrating deep reinforcement learning with sequence modeling for USV navigation.

KW - High-Fidelity Modeling

KW - LSTM

KW - SAC

KW - Trajectory Prediction

KW - USV

UR - https://www.scopus.com/pages/publications/105041348458

U2 - 10.1007/978-981-95-7664-7_16

DO - 10.1007/978-981-95-7664-7_16

M3 - 会议稿件

AN - SCOPUS:105041348458

SN - 9789819576630

T3 - Lecture Notes in Electrical Engineering

SP - 169

EP - 182

BT - Proceedings of 5th 2025 International Conference on Autonomous Unmanned Systems, ICAUS - Volume 4

A2 - Xie, Shaorong

A2 - Niu, Yifeng

A2 - Fu, Wenxing

A2 - Qu, Yi

PB - Springer Science and Business Media Deutschland GmbH

T2 - 5th International Conference on Autonomous Unmanned Systems, ICAUS 2025

Y2 - 17 October 2025 through 19 October 2025

ER -

Gao X, Liu X, Xu M. Research on Unmanned Surface Vehicle Trajectory Prediction Based on the SAC-LSTM Algorithm. In Xie S, Niu Y, Fu W, Qu Y, editors, Proceedings of 5th 2025 International Conference on Autonomous Unmanned Systems, ICAUS - Volume 4. Springer Science and Business Media Deutschland GmbH. 2026. p. 169-182. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-95-7664-7_16

Research on Unmanned Surface Vehicle Trajectory Prediction Based on the SAC-LSTM Algorithm

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this