Нейронные сети в решении задач судовождения
EDN: DEGXLP
Аннотация
Статья представляет собой обзор технологий нейронных сетей (НС), используемых при решении задач обеспечения плавания морских надводных объектов. Рассматриваются проблемы формирования траекторий движения, вопросы обнаружения, классификации и расхождения со встречными судами, а также комплексирования навигационных данных и устранения киберрисков.
Ключевые слова
искусственный интеллект,
навигационная безопасность плавания,
нейронная сеть,
безэкипажные суда,
траектория,
обнаружение,
осведомленность,
классификация,
расхождение,
комплексирование,
кибербезопасность
При поддержке: Работа выполнена при финансовой поддержке Санкт-Петербургского государственного университета, проект №116636233.
Об авторах
Н. В. Кузнецов
Санкт-Петербургский государственный университет
Россия
Россия
Кузнецов Николай Владимирович. Член-корреспондент РАН, заведующий кафедрой. Действительный член международной общественной организации «Академия навигации и управления движением»
Б. С. Ривкин
АО «Концерн «ЦНИИ «Электроприбор» (С.-Петербург)
Россия
Россия
Ривкин Борис Самуилович. Кандидат технических наук, начальник Центра компетенций в области навигации. Действительный член международной общественной организации «Академия навигации и управления движением»
Список литературы
1. Аль Битар Н., Гаврилов А. И., Халаф В. Методы на основе искусственного интеллекта для повышения точности интегрированной навигационной системы при отсутствии сигнала ГНСС. Аналитический обзор // Гироскопия и навигация. 2019. №4. С. 3–28.
2. Revolutionizing maritime safety with artificial intelligence (AI), Robotic Biz. Editorial, 2003, September 12.
3. Chen, X. et al., Application of Artificial Intelligence in Maritime Transportation, Journal of Marine Science and Engineering, 2024, no. 12.
4. Roy, G., Securing Shipping Lanes Through the Use of Artificial Intelligence, Securities.io, 2023, November 27.
5. Ривкин Б.С. Беспилотные суда. Навигация и не только // Гироскопия и навигация. 2021. №1. C. 111–132.
6. Murray, B. et al., Approvable AI for Autonomous Ships: Challenges and Possible Solutions, Proceedings of the 32nd European Safety and Reliability Conference, 2022, doi: 10.3850/978-18-5183-4_S05-01-186-cd.
7. Родионов А.Г. и др. Искусственный интеллект в судовождении – игра в имитацию? // Морской вестник. 2022. №4. С. 95–102.
8. Lee, E. et al., An Efficient Feature Augmentation and LSTM-Based Method to Predict Maritime Traffic Condition, MDPI. Applied Science, 2023, no. 13.
9. Li, Y. et al., Deep learning-powered vessel traffic flow prediction with spatial-temporal attributes and similarity grouping, Engineering Applications of Artificial Intelligence, 2023, no. 126, part B.
10. Rakthanmanon, T. et al., Searching and Mining Trillions of Time Series Subsequences under Dynamic Time Warping, The 18th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Beijing, China, 12–16 August, 2012, pp. 262–270.
11. Yoo, B., Kim, J., Path optimization for marine vehicles in ocean currents using reinforcement learning, Journal of Marine Science and Technology, 2016, vol. 2, pp. 334–343.
12. Пашенцев С.В. Решение навигационной задачи Цермело для произвольного осевого поля скоростей // Вестник МГТУ. 2010. № 3. С. 587–591.
13. Guo, S. et al., An Autonomous Path Planning Model for Unmanned Ships Based on Deep Reinforcement Learning, Sensors, 2020, no. 20.
14. Lillicrap, T.P. et al., Continuous control with deep reinforcement learning, Computer Science, 2015, no. 8.
15. Zhu, Z. et al., Automatic collision avoidance algorithm based on route – plan-guided artificial potential field method, Ocean Engineering, 2023, vol. 271.
16. Hai Zhou et al., Ship trajectory prediction based on BP Neural Network, Journal on Artificial Intelligence, 2019, no. 1, pp. 29–36.
17. Yongfeng Suo et al., A Ship Trajectory Prediction Framework Based on a Recurrent Neural Network, Sensors, 2020, no. 20, doi: 10.3390/s201185133.
18. Capobianco S. et al., Deep Learning Methods for Vessel Trajectory Prediction Based on Recurrent Neural Networks, arXiv: 2101.02486, 2021, vol. 2.
19. Wenxiong Wu, et al. Ship trajectory prediction: An Integrated Approach Using ConvLSTM – Based Sequence to Sequence Model, Journal of Marine Science and Engineering, 2023, no. 11.
20. Соснин А.С., Суслова И.А. Функции активации нейросети: сигмоида, линейная, ступенчатая, RELU, TANH // Наука. Информатизация. Технологии. Образование: материалы ХII международной научно-практической конференции. Екатеринбург: Издательство РГППУ, 2019. С. 237–246.
21. Vaswani, A. et al., Attention Is All You Need, Advances in Neural Information Processing Systems 30, Proceedings of the 31st Annual Conference on Neural Information Processing Systems (NIPS), 4–9 December 2017, Long Beach, CA, USA.
22. Dapeng Jiang et al., TRFM – LS: Transformer-Based Deep Learning Method for Vessel Trajectory Prediction, Journal of Marine Science and Engineering, 2023, no. 11.
23. Huanhuan Li et al., Deep Bi-directional information-empowered ship trajectory prediction for maritime autonomous surface ships, Transportation Research. Part E, 2024, 181.
24. Vapnik, V.N., The Support Vector method, Artificial Neural Networks – ICANN’97, Lecture Notes in Computer Science, 1997, vol. 1327, Springer, Berlin, Heidelberg, https://doi.org/10.1007/BFb0020166.
25. Aziz, K., Bouchara, F., Multimodal Deep Learning for Robust Recognizing Maritime Imagery in the Visible and Infrared Spectrums, Image Analysis and Recognition. ICIAR 2018. Lecture Notes in Computer Science, vol. 10882, Springer, Cham., https://doi.org/10.1007/978-3-319-93000-8_27.
26. Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T., Caffe: convolutional architecture for fast feature embedding, Proceedings of the 22nd ACM International Conference on Multimedia, 2014, pp. 675–678.
27. Zhang, M.M., Choi, J., Daniilidis, K., Wolf, M.T., Kanan, C., VAIS: a dataset for recognizing maritime imagery in the visible and infrared spectrums, IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), June 2015, pp. 10–16.
28. Kwanghyum Kim et al., Probabilistic Ship Detection and Classification Using Deep Learning, Applied Sciencies. 2018. no. 8. https://doi.org/10.3390/app8060936.
29. Ren, S. et al., Faster R-CNN: Towards real-time object detection with region proposal networks, Advances in Neural Information Processing Systems, Morgan Kaufmann: San Mateo, CA, USA, 2015, pp. 91–99.
30. Girshick, R., Fast R-CNN, Proceedings of the IEEE 2015 Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7–12 June 2015, pp. 1440–1448.
31. Redmon, J. et al., You Only Look Once: Unified, Real-Time Object Detection, arXiv:1506.02640v5 [cs.CV], 9 May 2016.
32. Zhijian Huang et al., An Intelligent Ship Image/Video Detection and Classification Method with Improved Regressive Deep Convolutional Neural Network, Complexity, 2020, vol. 2020, issue 1, https://doi.org/10/1155/2020/1520872l.
33. Fei Gao et al., Anchor-free Convolutional Network with Dense Attention Feature Aggregation for Ship Detection in SAR Images, Remote Sensing, 2020, no. 12, doi:10.3390/rs12162619.
34. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C., Mobilenetv2: Inverted residuals and linear bottlenecks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 18–22 June 2018, Salt Lake City, UT, USA, pp. 4510–4520.
35. Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S., Feature pyramid networks for object detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 21–26 July 2017, Honolulu, HI, USA, pp. 2117–2125.
36. Xian, S., Zhirui, W., Yuanrui, S., Wenhui, D., Yue, Z., Kun, F., Air-sar-ship-1.0: High resolution sar ship detection dataset, J. Radars, 2019, no. 8, pp. 852–862.
37. Hao Li et al., Enhanced YOLO v3 Tiny Network for Real-time Ship Detection from Visual Image, IEEE Access, 2021, vol. 9, pp. 16692–16706.
38. Liqiong Chen et al., Improved YOLOv3 Based on Attention Mechanism for Fast and Accurate Ship Detection in Optical Remote Sensing Images, Remote Sensing, 2021, no. 13.
39. Shao, Z. et al., SeaShips: A large-scale precisely annotated dataset for ship detection, IEEE Transactions Multimedia, 2018, vol. 20, no. 10, pp. 2593–2604.
40. Триполец О.Ю. Обзор существующих методов расхождения безэкипажных судов // Вестник Государственного университета морского и речного флота имени адмирала С.О.Макарова. 2021. Т. 13. №4.
41. Sawada, R. et al., Automatic ship collision avoidance using deep reinforcement learning with LSTM in continuous action space, Journal of Marine Science and Technology, 2020, 1–16, doi: 10.1007/s00773-020-00755-0.
42. Imazu, H., Evaluation method of collision risk by using true motion, TransNav., 2017, vol. 11, no. 1, pp. 65–70.
43. Brockman, G. et al., Open AI gym., arXiv: 1606.01540, 2016.
44. Nomoto, K., Analysis of kempf’s standard maneuver test and proposed steering quality indices, Proceedings of the 1st symposium on ship manoeuvrability, 1960, pp. 275–304.
45. Luman Zhao et al., Control method for path following and collision avoidance of autonomous ship based on deep reinforcement learning, Journal of Marine Science and Technology, 2019, vol. 27, no. 4, pp. 293–310.
46. Fossen, T.I., Handbook of Marine Craft Hydrodynamics and Motion Control, John Wiley and Sons Ltd., 2011.
47. Fossen, T.I. et al., Line-of-sight path following of underactuated marine craft, Proceedings of the 6th IFAC Conference on Manoeuvring and Control of Marine Craft (MCMC 2003), pp. 211–216.
48. Вермишев Ю.Х. Основы управления ракетами. М.: Оборонгиз, 1968.
49. Schulman, J. et al., Proximal Policy Optimization, arXiv: 1707.06347(cs), 2017.
50. Guan Wei, Wang Kuo, COLREGs – Compliant Multi-Ship Collision Avoidance Based on Multi-Agent Reinforcement Learning Technique, Journal of Marine Science and Technology, 2022, no. 10.
51. Alonso-Mora, J. et al., Optimal Reciprocal Collision Avoidance for Multiple Non-Holonomic Robots, Springer. Berlin/Heidelberg, Germany, 2013, pp. 203–216.
52. Oliehoek, F.A. et.al., Optimal and approximate q-value functions for decentralized POMDPs, Artificial Intelligence Research, 2008, no. 32, pp. 289–353.
53. Yihan Niu et al., A Multi-Ship Collision Avoidance Algorithm Using Data-Driven Multi-Agent Deep Reinforcement Learning, Journal of Marine Science and Engineering, 2023, no. 11.
54. Chen, C. et al., A Novel Ship Collision Avoidance Awareness Approach for Cooperating Ships Using Multi-Agend Deep Reinforcement Learning, Journal of Marine Science and Engineering, 2021, no. 9.
55. Zhu, F. et al., Randomly Testing an Autonomous Collision Avoidance System with Real-World Ship Encounter Scenario from AIS Data, Journal of Marine Science and Engineering, 2022, no. 10.
56. Liu, J., Collision Avoidance for Underactuatrd Ocean-Going Vessel Considering COLREGs Constraints., IEEE Access, 2021, no. 9.
57. Hai-fa Dai et al., An INS/GNSS integrated navigation in GNSS denied environment using recurrent neural network, Defence Technology, 2020, no. 16, pp. 334–340.
58. Mehdi Aslinezhad et al., ANN – assisted robust GPS/INS information fusion to bridge GPS outage, EUROSIP Journal on Wireless Communications and Networking, 2020, 129, https://doi.org/10,1186/s13638-020-01747-9.
59. Chuang Zhang et al., Information Fusion Based on Artificial Intelligence Method for SINS/GPS Integrated Navigation of Marine Vessel, Journal of Electrical Engineering & Technology, 2020, no. 15, pp. 1345–1356.
60. Li, J. et al., Improving positional accuracy of vehicular navigation system during GPS outages utilizing ensemble learning algorithm, Information Fusion, 2017, vol. 35, pp. 1–10.
61. Taghizadeh, S., Safabakhsh, R., An integrated INS/GNSS system with an attention based hierarchial LSTM during GNSS outage, GPS Solutions, 2023, vol. 27.
62. Gandhi, A., Sharma, A., Biswas, A., Deshmukh, O., Gethr-net: A generalized temporally hybrid recurrent neural network for multi-modal information fusion, European Conference on Computer Vision, Springer, Cham., Netherlands, Amsterdam, 2016, 8–16, pp. 883–899.
63. Jiwoon Yoo and Yonghyun Yo, Formulating Cybersecurity Requirements for Autonomous Ships Using the SQUARE Methology, Sensors, 2023, no. 23.
64. Ривкин Б.С. Кибербезопасность на море. Навигационный аспект // Гироскопия и навигация. 2023. №4. С. 167–191.
65. Wilson, A. et al., Multi-Agent Reinforcement Learning for Maritime Operational Technology Cyber Security, CAMLIS’23: Conference on Applied Machine Learning for Information Security, October 19–20, 2023, Arlington, VA.
66. de Witt, C.S. et al., Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?, arXiv:2011.09533 [cs], 2020, URL: http://arxiv.org/abs/2011.09533.
67. Yu, C. et al., The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games, arXiv:2103.01955 [cs], 2022, URL: http://arxiv.org/abs/2103.01955.
68. Nistor, A., Cezar, S., Marine Applications: The Future of Autonomous Maritime Transportation and Logistics, doi: 10.5772/ intechopen.1004275.
69. Shostack, A., Threat Modeling: Designing for Security, 1st edn, Wiley, Hoboken, 2014.
70. Rumelhart, D.E., Hinton, G.E., Williams, R.J., Learning Internal Representations by Error Propagation, Parallel Distributed Processing, 1986, vol. 1, pp. 318–362.
71. Zhao, X., et al. A review of convolutional neural network in computer vision, Artificial Intelligence Review, 2024, vol. 57.
72. Wang, X. et al., Deep Reinforcement Learning: A Survey, IEEE Transactions on Neural Network and Learning Systems, 2024, vol. 35, issue 4.
73. Chiang, K.W. et al., Multisensor integration using neuron computing for land-vehicle navigation, GPS Solutions, 2003, vol. 6, no. 4, pp. 209–218.
74. Sharaf, R. et al., Online INS/GPS integration with a radial basis function neural network, IEEE Aerospace Electronic System Magazine, 2005, vol. 20, no. 3, pp. 8–14.
75. Liu, O., Deep Reinforcement Learning for Motion Control Algorithms in Robotic, Transactions on Computer Science and Systems Research, 2024, vol. 5.
76. Klinsmann, A. et al., Large Language Model-based Decision-making for COLREGs and the Control of Autonomous Surface Vehicles, arXiv:2411.16587v2 [cs.RO], 27 Nov. 2024.
77. Sarhadi, P., Naeem, W., and Athanasopoulos, N., An integrated risk assessment and collision avoidance methodology for an autonomous catamaran with fuzzy weighting functions, UKACC 13th International Conference on Control (CONTROL), 2022, pp. 228–234.
78. Qiang Zhu et al., YOLOv7-CSAW for maritime target detection, Front. Neurorobot, 2023, vol. 17, https://doi.org/10.3389/Fnbot.2023.1210470.
79. Степанов О.А. Нейросетевые алгоритмы в задаче нелинейного оценивания. Взаимосвязь с байесовским подходом // Материалы докладов XI конференции молодых ученых «Навигация и управление движением». Санкт-Петербург, 2009. С. 39–65.
80. Stepanov, O.A. et al., Adaptive algorithms for vessel roll prediction based on the Bayesian approach, 30th Mediterranean Conference on Control and Automation (MED), 2022, pp. 713–718.
Рецензия
Для цитирования:
Кузнецов Н.В., Ривкин Б.С. Нейронные сети в решении задач судовождения. Гироскопия и навигация. 2025;33(1):3-35. EDN: DEGXLP
For citation:
Kuznetsov N.V., Rivkin B.S. Neural Networks in Ship Navigation. Gyroscopy and Navigation. 2025;33(1):3-35. (In Russ.) EDN: DEGXLP
Просмотров:
70
Послать статью по эл. почте 