“eXogenous Kalman Filter (XKF) for Visualization and Motion Prediction of Ships using Live Automatic Identification System (AIS) Data”

Authors: Sindre Fossen and Thor I. Fossen,
Affiliation: NTNU and NTNU, Department of Engineering Cybernetics
Reference: 2018, Vol 39, No 4, pp. 233-244.

Keywords: Motion prediction, state estimation, autonomy, decision support, ship

Abstract: This paper addresses the problem of ship motion estimation using live data from Automatic Identification Systems (AIS). A globally exponentially stable observer for visualization and motion prediction of ships has been designed. Instead of using the extended Kalman filter (EKF) to deal with the kinematic nonlinearities the eXogenous Kalman Filter (XKF) is applied and by this global stability properties are proven. The proposed observer was validated using live AIS data from the Trondheim harbor in Norway and it was demonstrated that the observer tracks ships in real time. It was also demonstrated that the observer can predict the future motion of ships. The motion prediction capabilities are very useful for decision-support systems since this can be used to improve situational awareness e.g. for manned and unmanned autonomous ships that operate in common waters.

PDF PDF (9896 Kb)        DOI: 10.4173/mic.2018.4.1

DOI forward links to this article:
[1] Haitong Xu, Thor I. Fossen and C. Guedes Soares (2019), doi:10.1016/j.ejcon.2019.09.007
[2] Sindre Fossen, Robin T. Bye and Ottar L. Osen (2018), doi:10.1109/EECS.2018.00048
References:
[1] Andrisani, D. and Gau, C.F. (1987). Andrisani, D, and Gau, C.F. Estimation Using a Multirate Filter. IEEE Transactions on Automatic Control. 32(7):653--656. doi:10.1109/TAC.1987.1104672
[2] Automatic Identification System. (2018). Automatic Identification System, Wikipedia. Accessed 2018-02-15. https://en.wikipedia.org/wiki/Automatic_identification_system. .
[3] Bhat, S.P. and Bernstein, D.S. (2000). Bhat, S, P. and Bernstein, D.S. A Topological Obstruction to Continuous Global Stabilization of Rotational Motion and the Unwinding Phenomenon. Systems and Control Letters. 39(1):63--70. doi:10.1016/S0167-6911(99)00090-0
[4] Cristi, R. and Tummala, M. (2000). Cristi, R, and Tummala, M. Multirate, Multiresolution, Recursive Kalman Filter. Signal Processing. 80. doi:10.1016/S0165-1684(00)00104-3
[5] Farrell, J.A. (2008). Farrell, J, A. Aided Navigation: GPS with High Rate Sensors. McGraw-Hill. .
[6] Fossen, S. and Fossen, T.I. (2018). Fossen, S, and Fossen, T.I. Extended Kalman Filter Design and Motion Prediction of Ships using Live Automatic Identification System (AIS) Data. In Proc. of the 2nd European Conference on Electrical Engineering and Computer Science (EECS'18). Bern, Switzerland. .
[7] Fossen, T.I. (2011). Fossen, T, I. Handbook of Marine Craft Hydrodynamics and Motion Control. Wiley. doi:10.1002/9781119994138
[8] Fu, H. F.H., Liu, S. L.S., and Sun, F. S.F. (2010). Fu, H, F.H., Liu, S. L.S., and Sun, F. S.F. Ship Motion Prediction based on AGA-LSSVM. In IEEE International Conference on Mechatronics and Automation (ICMA'10). pages 202--206. doi:10.1109/ICMA.2010.5589093
[9] Gelb, A. (1974). Gelb, A, Applied Optimal Estimation. MIT Press. .
[10] Jaskolski, K. (2017). Jaskolski, K, Automatic Identification System (AIS) Dynamic Data Estimation Based on Discrete Kalman Filter (KF) Algorithm. Scientific Journal of Polish Naval Academy. 211(4):71---87. doi:10.5604/01.3001.0010.6747
[11] Jiang, S., Jin, H., and Wei, F. (2013). Jiang, S, , Jin, H., and Wei, F. LS-SVM Application for Ship Course Model Predictive Control. In IEEE International Conference on Mechatronics and Automation (ICMA'13). pages 1615---1619. doi:10.1109/ICMA.2013.6618156
[12] Johansen, T.A. and Fossen, T.I. (2017). Johansen, T, A. and Fossen, T.I. The eXogenous Kalman Filter (XKF). International Journal of Control. 90(2):161--167. doi:10.1080/00207179.2016.1172390
[13] Khalil, H.K. (2014). Khalil, H, K. Nonlinear Systems. Pearson, 3rd edition. .
[14] Lin, Z., Yang, Q., Guo, Z., and Li, J. (2011). Lin, Z, , Yang, Q., Guo, Z., and Li, J. An Improved Autoregressive Method with Kalman Filtering Theory for Vessel: Motion Predication. International Journal of Intelligent Systems. 4(4):11--18. .
[15] Mazzarella, F., Arguedas, V.F., and M.Vespe. (2015). Mazzarella, F, , Arguedas, V.F., and M.Vespe. Knowledge-based Vessel Position Prediction using Historical AIS Data. In Sensor Data Fusion: Trends, Solutions, Applications. pages 1--5. .
[16] Perera, L.P. and Soares, C.G. (2010). Perera, L, P. and Soares, C.G. Ocean Vessel Trajectory Estimation and Prediction Based on Extended Kalman Filter. In 2nd International Conference on Adaptive and Self-adaptive Systems and Applications. pages 14--20. .
[17] Ristic, B., Scala, B.L., Morelande, M., and Gordon, N. (2008). Ristic, B, , Scala, B.L., Morelande, M., and Gordon, N. Statistical Analysis of Motion Patterns in AIS Data: Anomaly Detection and Motion Prediction. In International conference on Information Fusion. pages 40--46. .
[18] Sapankevych, N. and Sankar, R. (2009). Sapankevych, N, and Sankar, R. Time Series Prediction using Support Vector Machines: A Survey. IEEE Comput. Intell. Mag.. 4(2):24--38. doi:10.1109/MCI.2009.932254
[19] Triantafyllou, M.S. and Bodson, M. (1982). Triantafyllou, M, S. and Bodson, M. Real-Time Prediction of Marine Vessel Motions Using Kalman Filtering Techniques. In Annual Offshore Technology Conference. page14. doi:doi.org/10.4043/4388-MS
[20] Unity. (2018). Unity, The Unity Game Engine. Accessed 2018-08-17. https://unity3d.com. .
[21] US Coast Guard. (2018). US Coast Guard, Navigation Centre. Accessed 2018-02-15. https://www.navcen.uscg.gov/?pageName=AISMessages, doi:10.1016/0003-4916(63)90068-X
[22] Xiao, Z., Ponnambalam, L., Fu, X., and Zhang, W. (2017). Xiao, Z, , Ponnambalam, L., Fu, X., and Zhang, W. Maritime Traffic Probabilistic Forecasting Based on Vessels' Waterway Patterns and Motion Behaviors. IEEE Transportation Intelligent Transportation Systems. 18(11):3122--3134. doi:10.1109/TITS.2017.2681810
[23] Yin, J. and Zou, Z. (2011). Yin, J, and Zou, Z. A Combined Modular Parametric and Non-parametric Method for Planar Ship Motion's On-line Prediction. In Lecture Notes in Informatics in Control, Automation and Robotics, volume1. pages 17--24. .
[24] Yin, J.C., Zou, Z.J., and Xu, F. (2013). Yin, J, C., Zou, Z.J., and Xu, F. On-line Prediction of Ship Roll Motion during Maneuvering using Sequential Learning RBF Neural Networks. Ocean Engineering. 61(139--147). doi:10.1016/j.oceaneng.2013.01.005
[25] Yumori, I. (1981). Yumori, I, Real Time Prediction of Ship Response to Ocean Waves Using Time Series Analysis. In Oceans'81. pages 1082---1089. doi:10.1109/OCEANS.1981.1151574


BibTeX:
@article{MIC-2018-4-1,
  title={{eXogenous Kalman Filter (XKF) for Visualization and Motion Prediction of Ships using Live Automatic Identification System (AIS) Data}},
  author={Fossen, Sindre and Fossen, Thor I.},
  journal={Modeling, Identification and Control},
  volume={39},
  number={4},
  pages={233--244},
  year={2018},
  doi={10.4173/mic.2018.4.1},
  publisher={Norwegian Society of Automatic Control}
};