A method of ship trajectory prediction based on MG-Transformer model

WANG Miaomiao, WANG Yanfu, YUAN Siying, YU Weizhe

doi:10.16411/j.cnki.issn1006-7736.2025.02.006

Journal of Dalian Maritime University >

2025 , Vol. 51 >Issue 2: 49 - 57

DOI: https://doi.org/10.16411/j.cnki.issn1006-7736.2025.02.006

A method of ship trajectory prediction based on MG-Transformer model

Expand

Online published: 2024-11-14

Fold

Abstract

Ship trajectory prediction is essential for intelligent ships to understand complex encounter scenarios and make wise decisions. However, due to inherent uncertainty and complex interactions between different ships, predicting future trajectories is a very challenging problem. Therefore, a ship trajectory prediction model based on Multi-relational weighted graph Transformer (MG-Transformer) is proposed. First, the motion patterns of ships with similar trajectories are extracted from AIS data to capture different movement features. On this basis, the historical motion patterns of different ships are learned to improve the prediction accuracy and efficiency of the model. Secondly, the multi-relational weighted graphs is constructed to illustrate the complex spatial relationship between multiple ships. The interaction with surrounding ships is learned through Transformer to refine the trajectory and predict a reasonable trajectory. The AIS data of Ningbo-Zhoushan Port is used for experimental verification. The results show that when predicting trajectories of different time steps, compared with LSTM, BiLSTM, Seq2seq, and Social-SGCNN, the MG-Transformer model has a significant decrease in the average displacement error and final displacement error indicators. The average reduction of each indicator is 27.54%. The accuracy of the proposed ship trajectory prediction model has been significantly improved, which is crucial for maritime traffic safety and efficiency.

Key words： intelligent ships; AIS data; behavior patterns; trajectory prediction; multi-relational weighted graphs

Cite this article

WANG Miaomiao, WANG Yanfu, YUAN Siying, YU Weizhe . A method of ship trajectory prediction based on MG-Transformer model[J]. Journal of Dalian Maritime University, 2025 , 51(2) : 49 -57 . DOI: 10.16411/j.cnki.issn1006-7736.2025.02.006

References

[1] 黄亮, 刘益, 文元桥, 等. 内河渡船异常行为识别[J]. 大连海事大学学报, 2017, 43(1): 8-13.

HUANG L, LIU Y, WEN Y Q, et al. Abnormal behavior recognition of inland river ferryboa[J]. Journal of Dalian Maritime University, 2017, 43(1): 8-13. (in Chinese)

[2] 崔志远, 潘明阳, 林治家, 等. 一种基于GAN的多船轨迹预测方法[J]. 大连海事大学学报, 2023, 49(3): 51-60.

CUI Z Y, PAN M Y, LIN Z J, et al. A GAN based multi-vessel trajectory prediction method[J]. Journal of Dalian Maritime University, 2023, 49(3): 51-60. (in Chinese)

[3] GAO D W, ZHU Y S, SOARES C G. Uncertainty modelling and dynamic risk assessment for long-sequence AIS trajectory based on multivariate Gaussian Process[J]. Reliab Eng Syst Saf, 2023, 230: 108963.

[4] 张英俊, 翟鹏宇. 海运船舶自主避碰技术研究进展与趋势[J]. 大连海事大学学报, 2022, 48(3): 1-11.

ZHANG Y J, ZHAI P Y. Research progress and trend of autonomous collision avoidance technology for marine ships[J]. Journal of Dalian Maritime University, 2022, 48(3): 1-11. (in Chinese)

[5] SCHöLLER C, ARAVANTINOS V, LAY F, et al. What the constant velocity model can teach us about pedestrian motion prediction[J]. IEEE Rob Autom Lett, 2020, 5(2): 1696-703.

[6] LI X R, JILKOV V P. Survey of maneuvering target tracking. Part I. Dynamic models[J]. IEEE Trans Aerosp Electron Syst, 2003, 39(4): 1333-64.

[7] 茅晨昊, 潘晨, 尹波, 等. 基于高斯过程回归的船舶航行轨迹预测[J]. 科技创新与应用, 2017(31): 28-29+31.

MAO C H, PAN C, YIN B, et al. Ship trajectory prediction based on Gaussian process regression[J]. Technology Innovation and Application, 2017(31): 28-29+31. (in Chinese)

[8] 甄荣, 石自强. 一种基于高斯混合模型的船舶航迹聚类方法[J]. 船舶工程, 2021, 43(11): 139-143.

ZHEN R, SHI Z Q. Ship trajectory clustering method based on gaussian mixture model[J]. Ship Engineering, 2021, 43(11): 139-143. (in Chinese)

[9] PERERA L P, OLIVEIRA P, SOARES C G. Maritime traffic monitoring based on vessel detection, tracking, state estimation, and trajectory prediction[J]. IEEE Trans Intell Transp Syst, 2012, 13(3): 1188-200.

[10] MILLEFIORI L M, BRACA P, BRYAN K, et al. Modeling vessel kinematics using a stochastic mean-reverting process for long-term prediction[J]. IEEE Trans Aerosp Electron Syst, 2016, 52(5): 2313-30.

[11] XIAO Z, FU X J, ZHANG L Y, et al. Big data driven vessel trajectory and navigating state prediction with adaptive learning, motion modeling and particle filtering techniques[J]. IEEE Trans Intell Transp Syst, 2020, 23(4): 3696-709.

[12] CAPOBIANCO S, MILLEFIORI L M, FORTI N, et al. Deep learning methods for vessel trajectory prediction based on recurrent neural networks[J]. IEEE Trans Aerosp Electron Syst, 2021, 57(6): 4329-46.

[13] LI H H, JIAO H, YANG Z L. AIS data-driven ship trajectory prediction modelling and analysis based on machine learning and deep learning methods[J]. Transportation Research Part E: Logistics and Transportation Review, 2023, 175: 103152.

[14] 徐瑞龙, 祁云嵩, 石琳. 基于Transformer模型和Kalman滤波预测船舶航迹[J]. 计算机应用与软件, 2021, 38(5):106-111.

XU R L, QI Y S, SHI L. Prediction of ship track based on transformer model and kalman filter[J]. Computer Applications and Software, 2021, 38(5):106-111. (in Chinese)

[15] LIU R W, LIANG M H, NIE J T, et al. Deep learning-powered vessel trajectory prediction for improving smart traffic services in maritime Internet of Things[J]. IEEE Trans Network Sci Eng, 2022, 9(5): 3080-94.

[16] 黄敏, 杨亚东, 吴新鹏. 基于时空注意力机制的STA-GRU船舶轨迹预测方法[J]. 交通信息与安全, 2023, 41(6): 82-89.

HUANG M, YANG Y D,WU X P. Ship trajectory prediction method of gated recurrent unit based on spatial-temporal attention mechanism[J]. Journal of Transport Information and Safety, 2023, 41(6): 82-89. (in Chinese)

[17] MOHAMED A, QIAN K, ELHOSEINY M, et al. Social-stgcnn: A social spatio-temporal graph convolutional neural network for human trajectory prediction[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020:14412-14420.

[18] FENG H, CAO G, XU H X, et al. IS-STGCNN: An Improved Social spatial-temporal graph convolutional neural network for ship trajectory prediction[J]. Ocean Eng, 2022, 266: 112960.

[19] CAMPELLO R J, MOULAVI D, SANDER J. Density-based clustering based on hierarchical density estimates[C]// Advances in Knowledge Discovery and Data Mining - 17th Pacific-Asia Conference, PAKDD 2013, Gold Coast, QLD, Australien, PART 2 Springer, 2013:160-172.

[20] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.

[21] ZHANG W B, JIANG W Y, LIU Q, et al. AIS data repair model based on generative adversarial network[J]. Reliab Eng Syst Saf, 2023, 240: 109572.

[22] GAO D W, ZHU Y S, ZHANG J F, et al. A novel MP-LSTM method for ship trajectory prediction based on AIS data[J]. Ocean Eng, 2021, 228: 108956.

[23] PARK J, JEONG J, PARK Y. Ship trajectory prediction based on bi-LSTM using spectral-clustered AIS data[J]. J Mar Sci Eng, 2021, 9(9): 1037.

[24] YOU L, XIAO S Y, PENG Q X, et al. St-seq2seq: A spatio-temporal feature-optimized seq2seq model for short-term vessel trajectory prediction[J]. IEEE Access, 2020, 8: 218565-74.

Options

Outlines

模态框（Modal）标题

Abstract

Cite this article

References