Optimal Prediction of Individual Vessel Trajectories Based on Sparse Gaussian Processes
Source abstract
Abstract
Accurate forecasting of ship encounter positions is crucial for preventing collisions at sea. This paper presents a framework for predicting a ship’s trajectory using a sparse Gaussian process. The proposed method effectively addresses the limitations of existing full Gaussian processes, specifically the significant storage requirements and time complexity associated with data training. The model is trained using Automatic Identification System (AIS) data on trajectories, with hyperparameters optimized through a genetic algorithm. Experimental analysis demonstrates that the proposed model reduces average time complexity by 61.3 s and improves average prediction error to 9.2 m compared to full Gaussian-process-based models.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Maritime Navigation and Safety · Gaussian Processes and Bayesian Inference · Ship Hydrodynamics and Maneuverability
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Mokpo Vessel Traffic Service Center, Korea Coast Guard Region-West, Mokpo 58625, Republic of Korea
References (46)
Show source-provided references
1. European Maritime Safety Agency (2021). Annual Overview of Marine Casualties and Incidents 2021, European Maritime Safety Agency.
2. Ship collision avoidance and COLREGS compliance using simulation-based control behavior selection with predictive hazard assessment10.1109/TITS.2016.2551780 ↗
3. Shi, Z., Xu, M., Pan, Q., Yan, B., and Zhang, H. (2018, January 8–13). LSTM-based flight trajectory prediction. Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil.10.1109/IJCNN.2018.8489734 ↗
4. Symbolic and Pictorial Displays for Submarine Control10.1109/THFE.1967.233958 ↗
5. Wen, Q., Sun, L., Yang, F., Song, X., Gao, J., Wang, X., and Xu, H. (2021, January 19–26). Time Series Data Augmentation for Deep Learning: A Survey. Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, Montreal, QC, Canada.10.24963/ijcai.2021/631 ↗
6. A Bayesian nonparametric approach to modeling motion patterns10.1007/s10514-011-9248-x ↗
7. Williams, C.K.I., and Rasmussen, C.E. (2006). Gaussian Processes for Machine Learning, MIT Press.
8. Jakkala, K. (2021). Deep Gaussian Processes: A Survey. arXiv.
9. A framework for evaluating approximation methods for Gaussian process regression
10. Some aspects of the spline smoothing approach to non-parametric regression curve fitting10.1111/j.2517-6161.1985.tb01327.x ↗
11. A unifying view of sparse approximate Gaussian process regression
12. Vapnik, V. (1998). Statistical Learning Theory, Wiley.
13. Practical Calculation Method of Ship Maneuvering Motion10.3233/ISP-1981-2832502 ↗
14. Effect of path prediction on navigational performance10.1017/S0373463397007662 ↗
15. Fossen, T.I. (2011). Handbook of Marine Craft Hydrodynamics and Motion Control, John Wiley & Sons.10.1002/9781119994138 ↗
16. Passenier, P.O., and Amerongen, J. (1987, January 6–9). An adaptive track predictor for ships. Proceedings of the 8th Ship Control Systems Symposium, The Hague, The Netherlands.
17. Maritime traffic monitoring based on vessel detection, tracking, state estimation, and trajectory prediction10.1109/TITS.2012.2187282 ↗
18. Fossen, S., and Fossen, T.I. (2018, January 20–22). Extended Kalman Filter design and motion prediction of ships using live automatic identification system (AIS) data. Proceedings of the 2018 2nd European Conference on Electrical Engineering and Computer Science (EECS), Bern, Switzerland.10.1109/EECS.2018.00092 ↗
19. Ristic, B., La Scala, B., Morelande, M., and Gordon, N. (July, January 30). Statistical analysis of motion patterns in AIS data: Anomaly detection and motion prediction. Proceedings of the 2008 11th International Conference on Information Fusion, Cologne, Germany.
20. Comprehensive Analysis of Automatic Identification System (AIS) Data in Regard to Vessel Movement Prediction10.1017/S0373463314000253 ↗
21. CPA calculation method based on AIS position prediction10.1017/S0373463316000229 ↗
22. What the constant velocity model can teach us about pedestrian motion prediction10.1109/LRA.2020.2969925 ↗
23. Detection of abnormal vessel behaviour based on probabilistic directed graph model10.1017/S0373463320000144 ↗
24. Ship Trajectory online prediction based on BP neural network algorithm
25. Maritime anomaly detection using density-based clustering and recurrent neural network10.1017/S0373463319000031 ↗
26. Ship trajectory prediction based on BP neural network10.32604/jai.2019.05939 ↗
27. Wang, C., Ren, H., and Li, H. (2020, January 11–12). Vessel trajectory prediction based on AIS data and bidirectional GRU. Proceedings of the 2020 International Conference on Computer Vision, Image and Deep Learning (CVIDL), Chongqing, China.10.1109/CVIDL51233.2020.00-89 ↗
28. Park, J., Jeong, J., and Park, Y. (2021). Ship trajectory prediction based on bi-LSTM using spectral-clustered AIS data. J. Mar. Sci. Eng., 9.10.3390/jmse9091037 ↗
29. A bi-directional lstm ship trajectory prediction method based on attention mechanism10.1109/IAEAC50856.2021.9391059 ↗
30. Ship trajectory uncertainty prediction based on a Gaussian Process model10.1016/j.oceaneng.2019.04.024 ↗
31. Idé, T., and Kato, S. (May, January 30). Travel-time prediction using Gaussian process regression: A trajectory-based approach. Proceedings of the 2009 SIAM International Conference on Data Mining, Sparks, NV, USA.10.1137/1.9781611972795.101 ↗
32. The origins of kriging10.1007/BF00889887 ↗
33. Clustering to minimize the maximum intercluster distance10.1016/0304-3975(85)90224-5 ↗
34. Preparata, F.P., and Shamos, M.I. (2012). Computational Geometry: An Introduction, Springer Science & Business Media.
35. Fast sparse Gaussian process methods: The informative vector machine
36. Holland, J. (1975). Adaptation in Natural and Artificial Systems, MIT Press.
37. Sivanandam, S.N., and Deepa, S.N. (2008). Introduction to Genetic Algorithms, Springer.
38. A new crossover operator for real coded genetic algorithms
39. A new mutation operator for real coded genetic algorithms
40. A Bayesian Nonparametric Approach to Modeling Mobility Patterns
41. (2022, November 01). Korean Maritime Safety Tribunal Statistics of Marine Accidents. Available online: www.kmst.go.kr.
42. Pellegrini, S., Ess, A., Schindler, K., and Van Gool, L. (October, January 27). You’ll never walk alone: Modeling social behavior for multi-target tracking. Proceedings of the 2009 IEEE 12th International Conference on Computer Vision, Kyoto, Japan.10.1109/ICCV.2009.5459260 ↗
43. Social LSTM: Human trajectory prediction in crowded spaces
44. A taxonomy of global optimization methods based on response surfaces10.1023/A:1012771025575 ↗
45. Robust adaptive asymptotic trajectory tracking control for underactuated surface vessels subject to unknown dynamics and input saturation10.1007/s00773-021-00835-9 ↗
46. HF-based sensorless control of a FTPMM in ship shaftless rim-driven thruster system10.1109/TITS.2022.3143208 ↗