VTP-STGMAN: Vessel Trajectory Prediction Based on an Improved Spatial-Temporal Graph Multi-Attention Network

Abstract

In busy and complex maritime areas, navigation safety is of paramount importance, and predicting vessel trajectory accurately and identifying potential collision risk in advance is one of the effective means. Existing methods often struggle to capture the intricate spatial interactions and nonlinear temporal dependencies of vessels. To address this challenge, we proposed a novel trajectory prediction model based on an improved spatial-temporal graph multi-attention network, VTP-STGMAN. First, we revise the calculation of distance to the closest point of approach (DCPA), and navigational metrics, including the revised DCPA, time to the closest point of approach (TCPA) and actual distances among vessels, are applied to redesign the calculation method of the attention score in the graph attention network (GAT). The improved GAT model can extract the spatial features of multiple vessel trajectories accurately. Secondly, we integrate an attention mechanism with the temporal convolutional network (TCN) to adaptively capture nonlinear temporal correlation of trajectories. Finally, the probability distribution of the future trajectory rather than a deterministic trajectory of a vessel is predicted. It can reflect the inherent uncertainty of ship motion in the real world more accurately, and allow the collision avoidance decision system to minimize the risk expectation based on multiple high probability trajectories. Numerous experiments are conducted on real-world automatic identification system (AIS) data from Zhoushan (China) and Denmark. Evaluated results demonstrate that VTP-STGMAN can significantly outperform state-of-the-art baselines, reducing average displacement error (ADE) and final displacement error (FDE) by 23.6% and 29.7% in the primary benchmark respectively.

Keywords

Trajectory prediction / Graph attention network / Closest point of approach / Multi-vessel encounter scenarios / Automatic identification system

References

[1] Alahi A, Goel K, Ramanathan V, Robicquet A, Fei-Fei L, Savarese S. Social LSTM: Human trajectory prediction in crowded spaces. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 2016: 961-971

[2] Bai S, Kolter JZ, Koltun V (2018) An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. Computer Science: Machine Learning, arXiv:1803.01271

[3] Chen X, Luo F, Zhao F, Ye Q. Goal-guided and interaction-aware state refinement graph attention network for multi-agent trajectory prediction. IEEE Robot. Autom. Lett., 2024, 9(1): 57-64

[4] Dalsnes BR, Hexeberg S, Flaten AL, Eriksen BOH, Brekke EF. The neighbor course distribution method with Gaussian mixture models for AIS-based vessel trajectory prediction. 2018 21st International Conference on Information Fusion (FUSION), Cambridge, UK, 2018: 580-587

[5] Gao D, Zhu Y, Zhang J, He Y, Yan K, Yan B. A novel MP-LSTM method for ship trajectory prediction based on AIS data. Ocean Engineering, 2021, 228: 108956

[6] Gong J, Li H, Jiao H, Yang Z. Uncertainty-aware ship trajectory prediction via Spatio-Temporal Graph Transformer. Transportation Research Part E: Logistics and Transportation Review, 2025, 203: 104315

[7] Gupta A, Johnson J, Fei-Fei L, Savarese S, Alahi A. Social GAN: Socially acceptable trajectories with generative adversarial networks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 2255-2264

[8] Huang F, Liu Z, Li X, Mou F, Li P, Fan Z. Vessel trajectory prediction based on AIS data: Dual-path spatial-temporal attention network with multi-attribute information. J. Mar. Sci. Eng., 2024, 12(11): 2031

[9] Huang Y, Li Y, Zhang Z, Liu RW. GPU-accelerated compression and visualization of large-scale vessel trajectories in maritime IoT industries. IEEE Internet of Things Journal, 2020, 7(11): 10794-10812

[10] Jankowski D, Lamm A, Hahn A. Determination of AIS position accuracy and evaluation of reconstruction methods for maritime observation data. IFAC-PapersOnLine, 2021, 54(16): 97-104

[11] Lei H, Liu R, Chen J, Li H, Jia S. Vessel traffic flow prediction through multi-scale spatiotemporal attention in dual-graph networks. Transportation Research Part C: Emerging Technologies, 2026, 184: 105529

[12] Li Y, Wang S, Liu B, Fan S, Wang J. Decision-making algorithm based on Deep Q Network for ship collision avoidance. 2023 7th International Conference on Control Engineering and Artificial Intelligence, Sanya, China, 2023: 23-30

[13] Liu RW, Hu K, Liang M, Li Y, Liu X, Yang D. QSD-LSTM: Vessel trajectory prediction using long short-term memory with quaternion ship domain. Applied Ocean Research, 2023, 136: 103592

[14] Liu RW, Liang M, Nie J, Lim WYB, Zhang Y, Guizani M. Deep learning-powered vessel trajectory prediction for improving smart traffic services in maritime internet of things. IEEE Transactions on Network Science and Engineering, 2022, 9(5): 3080-3094

[15] Liu RW, Nie J, Garg S, Xiong Z, Zhang Y, Hossain MS. Data-driven trajectory quality improvement for promoting intelligent vessel traffic services in 6G-enabled maritime IoT systems. IEEE Internet of Things Journal, 2021, 8(7): 5374-5385

[16] Mohamed A, Qian K, Elhoseiny M, Claudel C. Social-STGCNN: A social spatio-temporal graph convolutional neural network for human trajectory prediction. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, 2020: 14412-14420

[17] Murray B, Perera LP. A dual linear autoencoder approach for vessel trajectory prediction using historical AIS data. Ocean Engineering, 2020, 209: 107478

[18] Nguyen D, Fablet R. A transformer network with sparse augmented data representation and cross entropy loss for AIS-based vessel trajectory prediction. IEEE Access, 2024, 12: 21596-21609

[19] Pellegrini S, Ess A, Schindler K, Van Gool L. You’ll never walk alone: Modeling social behavior for multi-target tracking. 2009 IEEE 12th International Conference on Computer Vision, Kyoto, Japan, 2009: 261-268

[20] Perera LP, Oliveira P, Guedes Soares C. Maritime traffic monitoring based on vessel detection, tracking, state estimation, and trajectory prediction. IEEE Trans. Intell. Transport. Syst., 2012, 13: 1188-1200

[21] Rossi L, Paolanti M, Pierdicca R, Frontoni E. Human trajectory prediction and generation using LSTM models and GANs. Pattern Recognition, 2021, 120: 108136

[22] Scholler C, Aravantinos V, Lay F, Knoll A. What the constant velocity model can teach us about pedestrian motion prediction. IEEE Robotics and Automation Letters, 2020, 5(2): 1696-1703

[23] Sekhon J, Fleming C. A spatially and temporally attentive joint trajectory prediction framework for modeling vessel intent. Proceedings of the 2nd Conference on Learning for Dynamics and Control, PMLR, 2020, 120: 318-327

[24] Thekumparampil KK, Wang C, Oh S, Li LJ (2018) Attention-based graph neural network for semi-supervised learning. Machine Learning, arXiv:1803.03735. https://doi.org/10.48550/arXiv.1803.03735

[25] Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. Advances in Neural Information Processing Systems, arXiv: 1706.03762. https://doi.org/10.48550/arXiv.1706.03762

[26] Wang C, Ren H, Li H. Vessel trajectory prediction based on AIS data and bidirectional GRU. 2020 International Conference on Computer Vision, Image and Deep Learning (CVIDL), Chongqing, China, 2020: 260-264

[27] Wang Z, Nie Z, Sheng G. Dynamic position predicting of underactuated surface vessel with unscented Kalman filter. 2018 Chinese Automation Congress (CAC), Xi’an, China, 2018: 4030-4033

[28] Wu L, Xu Y, Wang Q, Wang F, Xu Z. Mapping global shipping density from AIS data. J. Navig., 2017, 70(1): 67-81

[29] Xiao Y, Luo X, Wang T, Zhang Z. Spatio-temporal transformer networks for inland ship trajectory prediction with practical deficient automatic identification system data. Applied Sciences, 2024, 14: 10494

[30] Yan S, Xiong Y, Lin D. Spatial temporal graph convolutional networks for skeleton-based action recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 2018, 32(1): 12328

[31] Yan Z, Xiao Y, Cheng L, He R, Ruan X, Zhou X, Li M, Bin R. Exploring AIS data for intelligent maritime routes extraction. Appl. Ocean Res., 2020, 101: 102271

[32] Zhang R, Li C, Liu K, Wang C, Zheng B, Jiang H. Unified multimodal vessel trajectory prediction with explainable navigation intention. IEEE Transactions on Intelligent Transportation Systems, 2026, 27: 258-269

[33] Zhang Y, Sun X, Chen J, Cheng C. Spatial patterns and characteristics of global maritime accidents. Reliab. Eng. Syst. Saf., 2021, 206: 107310

RIGHTS & PERMISSIONS

Harbin Engineering University and Springer-Verlag GmbH Germany, part of Springer Nature

Just Accepted

This article has successfully passed peer review and final editorial review, and will soon enter typesetting, proofreading and other publishing processes. The currently displayed version is the accepted final manuscript. The officially published version will be updated with format, DOI and citation information upon launch. We recommend that you pay attention to subsequent journal notifications and preferentially cite the officially published version. Thank you for your support and cooperation.