Vessel trajectory prediction model based on spatio-temporal graph convolutional network with spatio-temporal joint attention mechanism

Abstract

With the development of vessel intelligence and the complexity of the maritime traffic environment, which brings new safety problems to maritime transport. Deep learning based on AIS data has become a research focus in maritime transportation. In this paper, a vessel trajectory prediction method based on the combination of spatio-temporal graph convolutional network and spatio-temporal joint attention mechanism (STA-GCNN) is proposed. Traditional vessel trajectory prediction is mostly based on single vessel historical data, ignoring the influence of interactions between vessels, so the prediction accuracy is insufficient in complex navigation environments. To improve this problem, we adopt a new method for calculating the interaction force between vessels, and we also use a joint spatio-temporal attention mechanism to make the model pay more attention to more important features, which realises the self-dynamic adjustment of the model’s focus. In this paper, experiments are conducted using AIS data from April 2022 in a US sea area. The results show that the method proposed in this paper has improved prediction accuracy in metrics such as Average Displacement Error (ADE) and Final Displacement Error (FDE) compared to existing LSTM-based and other conventional models.

Keywords

Trajectory prediction spatio-temporal graph convolutional network spatio-temporal joint attention mechanism interaction relations AIS data

Get full access to this article

View all access options for this article.

References

Pilatis

Pagonis

Serris

, et al. A statistical analysis of ship accidents (1990–2020) focusing on collision, grounding, hull failure, and resulting hull damage. J Mar Sci Eng 2024; 12: 122.

Robards

Silber

Adams

, et al. Conservation science and policy applications of the marine vessel automatic identification system (AIS)—a review. Bull Mar Sci 2016; 92(1): 75–10.

Capobianco

Millefiori

Forti

, et al. Deep learning methods for vessel trajectory prediction based on recurrent neural networks. IEEE Trans Aerosp Electron Syst 2021; 57(6): 4329–4346.

Liu

Liang

, et al. QSD-LSTM: vessel trajectory prediction using long short-term memory with quaternion vessel domain. Appl Ocean Res 2023; 136: 103592.

Zhang

Niu

, et al. Trajectory prediction for HF radar vessels submerged in strong clutter based on MSCNN fusion with GRU-AM and AR model. Remote Sens 2021; 13(11): 2164.

Jia

Yang

, et al. RAGAN: a generative adversarial network for risk-aware trajectory prediction in multi-vessel encounter situations. Ocean Eng 2023; 289: 116188.

Liu

Zheng

Liang

Spatio-temporal multi-graph transformer network for joint prediction of multiple vessel trajectories. Eng Appl Artif Intell 2024; 129: 107625.

Zhang

Chu

, et al. Model identification of vessel turning maneuver and extreme short-term trajectory prediction under the influence of sea currents. Ocean Eng 2023; 278: 114367.

Xiao

Zhang

, et al. Big data driven vessel trajectory and navigating state prediction with adaptive learning, motion modeling and particle filtering techniques. IEEE Trans Intell Transp Syst 2020; 23(4): 3696–3709.

10.

Shaojie

Kun

Nan

, et al. A trajectory prediction algorithm based on Gaussian mixture model. J Softw 2015; 26(5): 1048–1063.

11.

Fossen

. Exogenous kalman filter (XKF) for visualization and motion prediction of ships using live automatic identification systems (AIS) data. Model Identif Control 2018; 39(4): 233–244.

12.

Qiao

Tang

Jin

, et al. PutMode: prediction of uncertain trajectories in moving objects databases. Appl Intell 2010; 33: 370–386.

13.

Zhou

Chen

Zhang

Vessel trajectory prediction based on BP neural network. J Artif Intell 2019; 1(1): 29–36.

14.

Liu

Shi

Zhu

Vessel trajectory prediction model based on AIS sensor data and adaptive chaos differential evolution support vector regression (ACDE-SVR). Appl Sci 2019; 9(15): 2983.

15.

Zhang

Huang

Wen

, et al. Short-term trajectory prediction of maritime vessel using k-nearest neighbor points. J Mar Sci Eng 2022; 10(12): 1939.

16.

Zhang

Zhu

, et al. A hybrid prediction model based on KNN-LSTM for vessel trajectory. Mathematics 2022; 10(23): 4493.

17.

Zhang

Wang

Cui

, et al. Research into vessel trajectory prediction based on an improved LSTM network. J Mar Sci Eng 2023; 11(7): 1268.

18.

Kipf

Welling

Semi-supervised classification with graph convolutional networks. In: International conference on learning representations, 2017, pp.1–14.

19.

Mohamed

Qian

Elhoseiny

, et al. Social-STGCNN: a social spatio-temporal graph convolutional neural network for human trajectory prediction. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp.14412–14420.

20.

Huang

Liu

, et al. LSGCN: long short-term traffic prediction with graph convolutional networks. In: International joint conference on artificial intelligence, 2020, pp.2355–2361.

21.

Dai

Xiong

, et al. Deformable convolutional networks. In: IEEE international conference on computer vision, 2017, pp.764–773.

22.

Yan

Xiong

Lin

. Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI conference on artificial intelligence, 2018, vol. 32.

23.

Lea

Flynn

Vidal

, et al. Temporal convolutional networks for action segmentation and detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2017, pp.156–165.

24.

Lara-Benítez

Carranza-García

Luna-Romera

, et al. Temporal convolutional networks applied to energy-related time series forecasting. Appl Sci 2020; 10(7): 2322.

25.

Wang

Huang

Xiao

, et al. Medium-long-term prediction of water level based on an improved spatio-temporal joint attention mechanism for long short-term memory networks. J Hydrol 2023; 618: 129163.

26.

Yan

Xiong

Lin

. Spatial temporal graph convolutional networks for skeleton-based action recognition. In: AAAI Conference on Artificial Intelligence, 2018, pp.1–8.

27.

Zhang

Wang

Zhu

, et al. A bi-directional LSTM vessel trajectory prediction method based on attention mechanism. In: IEEE 5th advanced information technology, electronic and automation control conference (IAEAC), Chongqing, China, 2021, pp.1987–1993.

28.

Zhang

Ren

, et al. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: IEEE international conference on computer vision, 2015, pp.1026–1034.