Skip to main content

Advertisement

SpringerLink
Log in

A learning-based approach to surface vehicle dynamics modeling for robust multistep prediction

  • Published:
Autonomous Robots Aims and scope Submit manuscript

Abstract

Determining the dynamics of surface vehicles and marine robots is important for developing marine autopilot and autonomous navigation systems. However, this often requires extensive experimental data and intense effort because they are highly nonlinear and involve various uncertainties in real operating conditions. Herein, we propose an efficient data-driven approach for analyzing and predicting the motion of a surface vehicle in a real environment based on deep learning techniques. The proposed multistep model is robust to measurement uncertainty and overcomes compounding errors by eliminating the correlation between the prediction results. Additionally, latent state representation and mixup augmentation are introduced to make the model more consistent and accurate. The performance analysis reveals that the proposed method outperforms conventional methods and is robust against environmental disturbances.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  • Abbeel, P., & Ng, A. Y. (2005). Learning first-order markov models for control. Advances in neural information processing systems, 17, 1–8.

    Google Scholar 

  • Asadi, K. , Misra, D., Kim, S., & Littman, M.L. (2019). Combating the compounding-error problem with a multi-step model. arXiv preprint arXiv:1905.13320.

  • Asadi, K. , Misra, D., & Littman, M. (2018). Lipschitz continuity in model-based reinforcement learning. International conference on machine learning (pp. 264–273).

  • Cho, Y., Kim, J., & Kim, J. (2021). Intent inference-based ship collision avoidance in encounters with rule-violating vessels. IEEE Robotics and Automation Letters, 7(1), 518–525.

    Article  Google Scholar 

  • Co-Reyes, J., Liu, Y., Gupta, A., Eysenbach, B. , Abbeel, P., & Levine, S. (2018). Self-consistent trajectory autoencoder: Hierarchical reinforcement learning with trajectory embeddings. International conference on machine learning (pp. 1009–1018).

  • de Silva, B., Champion, K., Quade, M., Loiseau, J. C., Kutz, J., & Brunton, S. (2020). Pysindy: A python package for the sparse identification of nonlinear dynamical systems from data. Journal of Open Source Software, 5(49), 2104. https://doi.org/10.21105/joss.02104

    Article  Google Scholar 

  • Dimitrov, M. , Groves, K. , Howard, D. , & Lennox, B. (2021). Model identification of a small fully-actuated aquatic surface vehicle using a long short-term memory neural network. 2021 ieee international conference on robotics and automation (icra) (pp. 5966–5972).

  • Fossen, T. I. (2011). Handbook of marine craft hydrodynamics and motion control. John Wiley & Sons.

    Book  Google Scholar 

  • Fu, H., Li, C. , Liu, X. , Gao, J. , Celikyilmaz, A., & Carin, L. (2019). Cyclical annealing schedule: A simple approach to mitigating kl vanishing. arXiv preprint arXiv:1903.10145.

  • Guo, X., Zhang, X., Tian, X., Li, X., & Lu, W. (2021). Predicting heave and surge motions of a semi-submersible with neural networks. Applied Ocean Research, 112, 102708.

    Article  Google Scholar 

  • Haddara, M. R., & Xu, J. (1998). On the identification of ship coupled heave-pitch motions using neural networks. Ocean Engineering, 26(5), 381–400.

    Article  Google Scholar 

  • Hwang, S., H., & Whang, S.E. (2021). Mixrl: Data mixing augmentation for regression using reinforcement learning. arXiv preprint arXiv:2106.03374.

  • Iwana, B. K., & Uchida, S. (2021). An empirical survey of data augmentation for time series classification with neural networks. Plos one, 16(7), e0254841.

    Article  Google Scholar 

  • Jiang, Y., Hou, X.R. , Wang, X.G. , Wang, Z.H. , Yang, Z.L., & Zou, Z.J. (2021). Identification modeling and prediction of ship maneuvering motion based on lstm deep neural network. Journal of Marine Science and Technology 1–13.

  • Kim, K., Kim, J., & Kim, J. (2021). Robust data association for multi-object detection in maritime environments using camera and radar measurements. IEEE Robotics and Automation Letters, 6(3), 5865–5872.

    Article  MathSciNet  Google Scholar 

  • Kingma, D.P., & Welling, M. (2013). Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114.

  • Kolter, J. Z., & Manek, G. (2019). Learning stable deep dynamics models. Advances in neural information processing systems, 32, 11128–11136.

    Google Scholar 

  • Krishnamurthy, P., Khorrami, F., & Fujikawa, S. (2005). A modeling framework for six degree-of-freedom control of unmanned sea surface vehicles. Proceedings of the 44th ieee conference on decision and control (pp. 2676–2681).

  • Krupnik, O., Mordatch, I., & Tamar, A. (2020). Multi-agent reinforcement learning with multi-step generative models. Conference on robot learning (pp. 776–790).

  • Liu, Y., Duan, W., Huang, L., Duan, S., & Ma, X. (2020). The input vector space optimization for lstm deep learning model in real-time prediction of ship motions. Ocean Engineering, 213, 107681.

    Article  Google Scholar 

  • Longo, J., & Stern, F. (2005). Uncertainty assessment for towing tank tests with example for surface combatant dtmb model 5415. Journal of ship research, 49(01), 55–68.

    Article  Google Scholar 

  • Mishra, N., Abbeel, P., & Mordatch, I. (2017). Prediction and control with temporal segment models. International conference on machine learning (pp. 2459–2468).

  • Mo, J., Islam, M. J., & Sattar, J. (2021). Fast direct stereo visual slam. IEEE Robotics and Automation Letters, 7(2), 778–785.

    Article  Google Scholar 

  • Niklas, K., & Pruszko, H. (2019). Full-scale cfd simulations for the determination of ship resistance as a rational, alternative method to towing tank experiments. Ocean Engineering, 190, 106435.

    Article  Google Scholar 

  • Oh, S. R., Sun, J., Li, Z., Celkis, E. A., & Parsons, D. (2009). System identification of a model ship using a mechatronic system. IEEE/ASME Transactions on Mechatronics, 15(2), 316–320.

    Google Scholar 

  • Ouyang, Z. L., & Zou, Z. J. (2021). Nonparametric modeling of ship maneuvering motion based on gaussian process regression optimized by genetic algorithm. Ocean Engineering, 238, 109699.

    Article  Google Scholar 

  • Puodziunas, J.M., & Somero, J.R. (2021). Predicting ship maneuvering through machine learning. Aiaa scitech 2021 forum (pp. 0475).

  • Sandbrink, K.J., Mamidanna, P., Michaelis, C., Mathis, M.W., Bethge, M., & Mathis, A. (2020). Task-driven hierarchical deep neural network models of the proprioceptive pathway. bioRxiv.

  • She, Y., Liu, S.Q. , Yu, P., & Adelson, E. (2020). Exoskeleton-covered soft finger with vision-based proprioception and tactile sensing. 2020 ieee international conference on robotics and automation (icra) (pp. 10075–10081).

  • Skulstad, R., Li, G., Fossen, T. I., Vik, B., & Zhang, H. (2020). A hybrid approach to motion prediction for ship docking-integration of a neural network model into the ship dynamic model. IEEE Transactions on Instrumentation and Measurement, 70, 1–11.

    Article  Google Scholar 

  • Sonnenburg, C. R., & Woolsey, C. A. (2013). Modeling, identification, and control of an unmanned surface vehicle. Journal of Field Robotics, 30(3), 371–398.

    Article  Google Scholar 

  • Talvitie, E. (2014). Model regularization for stable sample rollouts. Uai (pp. 780–789).

  • Tang, G., Lei, J., Shao, C., Hu, X., Cao, W., & Men, S. (2021). Short-term prediction in vessel heave motion based on improved lstm model. IEEE Access, 9, 58067–58078.

    Article  Google Scholar 

  • Thakur, A., & Gupta, S.K. (2011). Real-time dynamics simulation of unmanned sea surface vehicle for virtual environments. Journal of Computing and Information Science in Engineering 11(3).

  • Thurman, C. S., & Somero, J. R. (2020). Comparison of meta-modeling methodologies through the statistical-empirical prediction modeling of hydrodynamic bodies. Ocean Engineering, 210, 107566.

    Article  Google Scholar 

  • Velagic, J. (2006). Design of ship controller and ship model based on neural network identification structures. 2006 world automation congress (pp. 1–7).

  • Venkatraman, A., Hebert, M., & Bagnell, J.A. (2015). Improving multi-step prediction of learned time series models. Twenty-ninth aaai conference on artificial intelligence.

  • Wang, L., Wu, Q., Liu, J., Li, S., & Negenborn, R. R. (2019). State-of-the-art research on motion control of maritime autonomous surface ships. Journal of Marine Science and Engineering, 7(12), 438.

    Article  Google Scholar 

  • Wang, T., Li, G. , Hatledal, L.I. , Skulstad, R. , Æsøy, V., & Zhang, H. (2021). Incorporating approximate dynamics into data-driven calibrator: A representative model for ship maneuvering prediction. IEEE Transactions on Industrial Informatics.

  • Willard, J., Jia, X. , Xu, S., Steinbach, M., & Kumar, V. (2020). Integrating scientific knowledge with machine learning for engineering and environmental systems. arXiv preprint arXiv:2003.04919.

  • Woo, J., Park, J., Yu, C., & Kim, N. (2018). Dynamic model identification of unmanned surface vehicles using deep learning network. Applied Ocean Research, 78, 123–133.

    Article  Google Scholar 

  • Yin, Jc., Zou, Zj., & Xu, F. (2013). On-line prediction of ship roll motion during maneuvering using sequential learning rbf neuralnetworks. Ocean engineering, 61, 139–147.

    Article  Google Scholar 

  • Yin, S., & Xiao, B. (2016). Tracking control of surface ships with disturbance and uncertainties rejection capability. IEEE/ASME transactions on mechatronics, 22(3), 1154–1162.

    Article  Google Scholar 

  • Zhang, H., Cisse, M., Dauphin, Y.N., & Lopez-Paz, D. (2017). mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412.

Download references

Acknowledgements

This research was a part of the project titled ‘Development of AUV fleet and its operation system for maritime search’, funded by Korea Coast Guard, and supported by National R &D Program through the National Research Foundation of Korea (NRF) funded by Ministry of Science and ICT (NRF-2020M3C1C1A02086303).

Author information

Authors and Affiliations

  1. Department of Naval Architecture and Marine Engineering, University of Michigan, 2600 Draper Dr, Ann Arbor, MI, 48109, USA

    Junwoo Jang

  2. Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea

    Changyu Lee & Jinwhan Kim

Authors
  1. Junwoo Jang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Changyu Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jinwhan Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Junwoo Jang conceptualized the primary methods, implemented the proposed algorithm, produced the results, and wrote the main manuscript. Changyu Lee produced the dataset by conducting an experiment and preprocessing the data. Jinwhan Kim secured funding and directed the research. All authors reviewed the manuscript.

Corresponding author

Correspondence to Jinwhan Kim.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jang, J., Lee, C. & Kim, J. A learning-based approach to surface vehicle dynamics modeling for robust multistep prediction. Auton Robot 47, 797–808 (2023). https://doi.org/10.1007/s10514-023-10114-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10514-023-10114-8

Keywords

Search

Navigation