Abstract
A ship trajectory predictor plays a key role in the predictive decision making of intelligent marine transportation. For better prediction performance, the biggest technical challenge is how we incorporate prior knowledge, acquired during the design-stage experiments, into a data-driven predictor if the number of available real-world data is limited. This study proposes a new framework under co-simulation platform Vico for the development of a neural-network-based trajectory predictor with a pre-training phase. Vico enables a simplified vessel model to be constructed by merging a hull model, thruster models, and a controller using a co-simulation standard. Furthermore, it allows virtual scenarios, which describe what will happen during the simulation, to be generated in a flexible way. The fully-connected feedforward neural network is pre-trained with the generated virtual scenarios; then, its weights and biases are finetuned using a limited number of real-world datasets obtained from a target operation. In the case study, we aim to make a 30 s trajectory prediction of real-world zig-zag maneuvers of a 33.9m-length research vessel. Diverse virtual scenarios of zig-zag maneuvers are generated in Vico and used for the pre-training. The pre-trained neural network is further finetuned using a limited number of real-world data of zig-zag maneuvers. The present framework reduced the mean prediction error in the test dataset of the real-world zig-zag maneuvers by 60.8% compared to the neural network without the pre-training phase. This result indicates the validity of virtual scenario generation on the co-simulation platform for the purpose of the pre-training of trajectory predictors.
Supported by a grant from NRF, IKTPLUSS project No. 309323 “Remote Control Center for Autonomous Ship Support” in Norway.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Akiba, T., Sano, S., Yanase, T., Ohta, T., Koyama, M.: Optuna: a next-generation hyperparameter optimization framework. In: KDD 2019: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2623–2631. Association for Computing Machinery, Anchorage (2019). https://doi.org/10.1145/3292500.3330701
Hassani, V., Fathi, D., Ross, A., Sprenger, F., Selvik, Ø., Berg, T.E.: Time domain simulation model for research vessel Gunnerus. In: Proceedings of the International Conference on Offshore Mechanics and Arctic Engineering - OMAE, St. John’s, Newfoundland, Canada, vol. 7 (2015). https://doi.org/10.1115/OMAE201541786
Hatledal, L.I., Chu, Y., Styve, A., Zhang, H.: Vico: an entity-component-system based co-simulation framework. Simul. Modell. Pract. Theory 108(September 2020), 102243 (2021). https://doi.org/10.1016/j.simpat.2020.102243
Hatledal, L.I., Zhang, H., Collonval, F.: Enabling python driven co-simulation models with PythonFMU. In: 34th International ECMS Conference on Modelling and Simulation (2020). https://doi.org/10.7148/2020-0235
Huang, Y., Chen, L., Chen, P., Negenborn, R.R., Gelder, P.H.A.J.M.V.: Ship collision avoidance methods: state-of-the-art. Saf. Sci. 121(April 2019), 451–473 (2020). https://doi.org/10.1016/j.ssci.2019.09.018
Intelligent Systems Lab @ NTNU Aalesund: Intelligent Systems Lab webpage. http://org.ntnu.no/intelligentsystemslab/
Kawan, B., Wang, H., Li, G., Chhantyal, K.: Data-driven modeling of ship motion prediction based on support vector regression. In: Proceedings of the 58th Conference on Simulation and Modelling (SIMS 58) Reykjavik, Iceland, 25th–27th September 2017, vol. 138, pp. 350–354 (2017). https://doi.org/10.3384/ecp17138350
Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, pp. 1–15 (2015)
Mei, B., Sun, L., Shi, G.: White-black-box hybrid model identification based on RM-RF for ship maneuvering. IEEE Access 7, 57691–57705 (2019). https://doi.org/10.1109/ACCESS.2019.2914120
Norges teknisk-naturvitenskapelige universitet: Research vessel: R/V Gunnerus. https://www.ntnu.edu/oceans/gunnerus
Panigrahi, S., Nanda, A., Swarnkar, T.: A survey on transfer learning. Smart Innov. Syst. Technol. 194, 781–789 (2021). https://doi.org/10.1007/978-981-15-5971-6_83
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)
Perera, L.P.: Navigation vector based ship maneuvering prediction. Ocean Eng. 138(November 2016), 151–160 (2017). https://doi.org/10.1016/j.oceaneng.2017.04.017
Rong, H., Teixeira, A.P., Guedes Soares, C.: Ship trajectory uncertainty prediction based on a Gaussian Process model. Ocean Eng. 182(December 2018), 499–511 (2019). https://doi.org/10.1016/j.oceaneng.2019.04.024
Skulstad, R., Li, G., Fossen, T.I., Vik, B., Zhang, H.: A hybrid approach to motion prediction for ship docking - integration of a neural network model into the ship dynamic model. IEEE Trans. Instr. Meas. 70, 1–11 (2021). https://doi.org/10.1109/TIM.2020.3018568
Skulstad, R., Li, G., Fossen, T.I., Wang, T., Zhang, H.: A co-operative hybrid model for ship motion prediction. Model. Ident. Control: Norwegian Res. Bul. 42(1), 17–26 (2021). https://doi.org/10.4173/mic.2021.1.2
Wang, T., Li, G., Hatledal, L.I., Skulstad, R., Aesoy, V., Zhang, H.: Incorporating approximate dynamics into data-driven calibrator: a representative model for ship maneuvering prediction. IEEE Trans. Ind. Inform. 1 (2021). https://doi.org/10.1109/tii.2021.3088404
Wang, Y., Yao, Q., Kwok, J.T., Ni, L.M.: Generalizing from a few examples: a survey on few-shot learning. ACM Comput. Surv. 53(3), 1–34 (2020). https://doi.org/10.1145/3386252
Wang, Z., Zou, Z., Soares, C.G.: Identification of ship manoeuvring motion based on nu-support vector machine. Ocean Eng. 183(January), 270–281 (2019). https://doi.org/10.1016/j.oceaneng.2019.04.085
Zhao, L., Roh, M.I.: COLREGs-compliant multiship collision avoidance based on deep reinforcement learning. Ocean Eng. 191(May), 106436 (2019). https://doi.org/10.1016/j.oceaneng.2019.106436
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kanazawa, M., Hatledal, L.I., Li, G., Zhang, H. (2022). Co-simulation-Based Pre-training of a Ship Trajectory Predictor. In: Cerone, A., et al. Software Engineering and Formal Methods. SEFM 2021 Collocated Workshops. SEFM 2021. Lecture Notes in Computer Science, vol 13230. Springer, Cham. https://doi.org/10.1007/978-3-031-12429-7_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-12429-7_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-12428-0
Online ISBN: 978-3-031-12429-7
eBook Packages: Computer ScienceComputer Science (R0)