“Leveraging Past Experience for Path planning of Marine Vessel: A Docking Example”

Authors: Peihua Han, Guoyuan Li and Houxiang Zhang,
Affiliation: NTNU Aalesund
Reference: 2022, Vol 43, No 3, pp. 101-109.

Keywords: path planning, RRT*, conditional variational autoencoder, learning from past experience

Abstract: Path planning before maneuvering is crucial for the safe and efficient operations of marine vessels. The past successful human maneuvering experience can be leveraged to enable the safe and efficient path planning of vessels. In this paper, the previous successful maneuvering operations from ship operators are leveraged to find the optimal path. A deep conditional generative model is used to learn the distribution from those experiences. The model is then combined with the sampling-based RRT* planning algorithm to guide the search process. In this way, the theoretical guarantee of RRT* is preserved while the sampling process is more efficient. The docking operation is used as an example to validate the method. Experimental results show that the presented method not only improves the success rate and convergence speed to the optimal cost but also generalizes well to starting points beyond maneuvering experience.

PDF PDF (4723 Kb)        DOI: 10.4173/mic.2022.3.2

DOI forward links to this article:
[1] V. V. Golubov and S. V. Manko (2024), doi:10.32362/2500-316X-2024-12-1-7-14
[1] Anderlini, E., Parker, G.G., and Thomas, G. (2019). Docking control of an autonomous underwater vehicle using reinforcement learning, Applied Sciences. 9(17):3456. doi:10.3390/app9173456
[2] Bergman, K., Ljungqvist, O., Linder, J., and Axehill, D. (2020). An optimization-based motion planner for autonomous maneuvering of marine vessels in complex environments, In 2020 59th IEEE Conference on Decision and Control (CDC). IEEE, pages 5283--5290. doi:10.1109/CDC42340.2020.9303746
[3] Enevoldsen, T.T., Reinartz, C., and Galeazzi, R. (2021). Colregs-informed rrt* for collision avoidance of marine crafts, In 2021 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pages 8083--8089. doi:10.1109/ICRA48506.2021.9560909
[4] Han, P., Li, G., Cheng, X., Skjong, S., and Zhang, H. (2022). An uncertainty-aware hybrid approach for sea state estimation using ship motion responses, IEEE Transactions on Industrial Informatics. 18(2):891--900. doi:10.1109/TII.2021.3073462
[5] Higgins, I., Matthey, L., Pal, A., Burgess, C., Glorot, X., Botvinick, M., Mohamed, S., and Lerchner, A. (2016). beta-vae: Learning basic visual concepts with a constrained variational framework, In 2017 International Conference on Learning Representations (ICLR). 2016.
[6] Huh, J. and Lee, D.D. (2018). Efficient sampling with q-learning to guide rapidly exploring random trees, IEEE Robotics and Automation Letters. 3(4):3868--3875. doi:10.1109/IROS.2018.8593947
[7] Ichter, B., Harrison, J., and Pavone, M. (2018). Learning sampling distributions for robot motion planning, In 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pages 7087--7094. doi:10.1109/ICRA.2018.8460730
[8] Jalonen, R., Tuominen, R., and Wahlstroem, M. (2016). Remote and autonomous ships—the next steps: Safety and security in autonomous shipping—challenges for research and development, Rolls-Royce, Buckingham Gate, London: The Advanced Autonomous Waterborne Applications (AAWA). pages 56--73.
[9] Karaman, S. and Frazzoli, E. (2010). Incremental sampling-based algorithms for optimal motion planning, Robotics Science and Systems VI. 104(2).
[10] Karaman, S. and Frazzoli, E. (2011). Sampling-based algorithms for optimal motion planning, The international journal of robotics research. 30(7):846--894. doi:10.1177/0278364911406761
[11] Karaman, S., Walter, M.R., Perez, A., Frazzoli, E., and Teller, S. (2011). Anytime motion planning using the rrt, In 2011 IEEE International Conference on Robotics and Automation. IEEE, pages 1478--1483. doi:10.1109/ICRA.2011.5980479
[12] Kim, B., Kaelbling, L., and Lozano-Perez, T. (2018). Guiding search in continuous state-action spaces by learning an action sampler from off-target search experience, In Proceedings of the AAAI Conference on Artificial Intelligence, volume32. 2018. doi:10.1609/aaai.v32i1.12106
[13] Kingma, D.P. and Welling, M. (2013). Auto-encoding variational bayes, arXiv preprint arXiv:1312.6114.
[14] Kuo, Y.-L., Barbu, A., and Katz, B. (2018). Deep sequential models for sampling-based planning, In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pages 6490--6497.
[15] LaValle, S.M. and KuffnerJr, J.J. (2001). Randomized kinodynamic planning, The international journal of robotics research. 20(5):378--400. doi:10.1177/02783640122067453
[16] Martinsen, A.B., Lekkas, A.M., and Gros, S. (2019). Autonomous docking using direct optimal control, IFAC-PapersOnLine. 52(21):97--102. doi:10.1016/j.ifacol.2019.12.290
[17] Martinsen, A.B., Lekkas, A.M., and Gros, S. (2021). Optimal model-based trajectory planning with static polygonal constraints, IEEE Transactions on Control Systems Technology. doi:10.1109/TCST.2021.3094617
[18] Mirza, M. and Osindero, S. (2014). Conditional generative adversarial nets, arXiv preprint arXiv:1411.1784.
[19] Miyauchi, Y., Sawada, R., Akimoto, Y., Umeda, N., and Maki, A. (2022). Optimization on planning of trajectory and control of autonomous berthing and unberthing for the realistic port geometry, Ocean Engineering. 245:110390. doi:10.1016/j.oceaneng.2021.110390
[20] Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., etal. (2019). Pytorch: An imperative style, high-performance deep learning library, Advances in neural information processing systems. 32.
[21] Qureshi, A.H., Simeonov, A., Bency, M.J., and Yip, M.C. (2019). Motion planning networks, In 2019 International Conference on Robotics and Automation (ICRA). IEEE, pages 2118--2124. doi:10.1109/ICRA.2019.8793889
[22] Qureshi, A.H. and Yip, M.C. (2018). Deeply informed neural sampling for robot motion planning, In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pages 6582--6588. doi:10.1109/IROS.2018.8593772
[23] Shuai, Y., Li, G., Cheng, X., Skulstad, R., Xu, J., Liu, H., and Zhang, H. (2019). An efficient neural-network based approach to automatic ship docking, Ocean Engineering. 191:106514. doi:10.1016/j.oceaneng.2019.106514
[24] Skulstad, R., Li, G., Fossen, T.I., Vik, B., and 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. doi:10.1109/TIM.2020.3018568
[25] Sohn, K., Lee, H., and Yan, X. (2015). Learning structured output representation using deep conditional generative models, Advances in neural information processing systems. 28.
[26] Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting, The journal of machine learning research. 15(1):1929--1958.
[27] Tamar, A., Wu, Y., Thomas, G., Levine, S., and Abbeel, P. (2016). Value iteration networks, Advances in neural information processing systems. 29.
[28] Wang, J., Chi, W., Li, C., Wang, C., and Meng, M. Q.-H. (2020). Neural rrt*: Learning-based optimal path planning, IEEE Transactions on Automation Science and Engineering. 17(4):1748--1758. doi:10.1109/TASE.2020.2976560
[29] Zaccone, R. and Martelli, M. (2020). A collision avoidance algorithm for ship guidance applications, Journal of Marine Engineering & Technology. 19(sup1):62--75. doi:10.1080/20464177.2019.1685836

  title={{Leveraging Past Experience for Path planning of Marine Vessel: A Docking Example}},
  author={Han, Peihua and Li, Guoyuan and Zhang, Houxiang},
  journal={Modeling, Identification and Control},
  publisher={Norwegian Society of Automatic Control}