Simulation Study on Automatic Piloting of Ships in Typical Inland Waterways

DOI: https://doi.org/10.62517/jcte.202406309

Author(s)

Weixuan Hu

Affiliation(s)

Wuhan Technical College of Communications, Wuhan, Hubei, China

Abstract

This article is based on typical inland waterway channels in China and conducts autonomous navigation simulation experiments of the vessel in four types of ship encounter situations—overtaking, head-on meeting, crossing, and intersecting—on the OpenCPN software platform. The experiments have reached the following conclusions: Firstly, during the course-keeping phase, the course control method can make the vessel travel along the planned route normally and keep the ship's position within a small range near the planned route, which is in line with the practice of inland waterway vessel navigation; Secondly, during the collision avoidance phase, the collision avoidance decision method can provide reasonable and effective avoidance action plans for the vessel according to different situations and the "Inland Navigation Collision Regulations", ensuring that the target vessel passes outside the vessel's domain of the vessel, while also ensuring that the vessel's domain does not exceed the channel boundaries; Thirdly, in the resumption of navigation phase, the course control method can make the vessel return to the planned route to continue navigation after the collision avoidance task is completed, maintaining the vessel's adherence to the planned route.

Keywords

Autopilot; Pursuit Crossing; Head-on Encounters; Crossing Encounters; Cross-country Encounters

References

[1] Xu H, Lu Y, Feng H, Zhou Z. Multi-target trajectory prediction algorithm for ship intelligent navigation. Journal of Huazhong University of Science and Technology (Natural Science Edition).2024(5): 35-38. [2] Zhang X, Fu X, Xiao Z, et al. Vessel trajectory prediction in maritime transportation: current approaches and beyond. IEEE Transactions on Intelligent Transportation Systems, 2022: 75-79. [3] Tang T, Yin Y, Shen H. A model for vessel trajectory prediction based on long short-term memory neural network. Journal of Marine Engineering & Technology, 2019, 21(03): 102-103. [4] Feng H, Cao G, Xu H, et al. IS-STGCNN: An improved social spatial-temporal graph convolutional neural network for ship trajectory prediction. Ocean Engineering, 2022: 23-25. [5] Shi L, Wang L, Long C, et al. SGCN: Sparse graph convolution network for pedestrian trajectory prediction//IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, US: IEEE, 2021:66-73. [6] Sadeghian A, Kosaraju V, Sadeghian A, et al. Sophie: An attentive Gan for predicting paths compliant to social and physical constraints//IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE, 2019: 93-99. [7] Kosaraju V, Sadeghian A, Martín-Martín R, et al. Social bigot: Multimodal trajectory forecasting using bicycle-Gan and graph attention networks//33rd Annual Conference on Neural Information Processing Systems (NIPS). Vancouver, Canada: NIPS, 2019: 121-125. [8] Liu X. Automatic obstacle identification method for ship simulation system. Ship Science and Technology, 2022(11): 144-147. [9] Yan R, Xie H, Hua M, et al. Wide-area ship target recognition method based on motion and appearance features. Chinese Journal of Ship Research, 2022, 17(1): 227−234. [10] Luo X, Yin J, Li H. An automatic collision avoidance system of ships based on dynamic hierarchical potential field method. Journal of Shanghai Maritime University, 2020, 41(1): 1–7.