人工智能辅助的深海运载器探测技术研究进展

廖勇; 朱俊豪

doi:10.3969/j.issn.1000-1565.2025.03.008

河北大学学报(自然科学版) >

2025 , Vol. 45 >Issue 3: 299 - 308

DOI: https://doi.org/10.3969/j.issn.1000-1565.2025.03.008

人工智能辅助的深海运载器探测技术研究进展

廖勇 ,
朱俊豪

展开

廖勇(1982—),男,重庆大学副研究员,博士,主要从事智能信号与信息处理、数字技术及其应用方向研究.
E-mail:liaoy@cqu.edu.cn

收稿日期: 2024-10-14

网络出版日期: 2025-05-14

基金资助

重庆市自然科学基金资助项目(CSTB2023NSCQ-MSX0025)

收起

Research progress on artificial intelligence-assisted deep-sea vehicle exploration technology

LIAO Yong ,
ZHU Junhao

Expand

School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China

Received date: 2024-10-14

Online published: 2025-05-14

Fold

摘要

海洋作为人类重要的资源宝库,蕴藏着丰富的水体、矿产和生物资源,而深海环境复杂,制约了人类对其深入探索.发展深海探测技术,尤其是人工智能辅助的深海运载器探测技术,已成为提升科学认知和可持续资源开发的迫切需求.为此,本文系统综述了目前人工智能在水下导航及通信、水下路径规划及安全避障、水下目标检测与识别、潜水器故障诊断与容错控制等一系列深海运载器关键技术中的运用,指出了当前人工智能辅助深海探测面临的问题与挑战,分析了未来人工智能辅助深海运载器探测技术可能的发展趋势,为相关领域的研究提供参考.

关键词： 人工智能; 深海探测; 深海运载器; 深度学习; 神经网络

本文引用格式

廖勇 , 朱俊豪 . 人工智能辅助的深海运载器探测技术研究进展[J]. 河北大学学报(自然科学版), 2025 , 45(3) : 299 -308 . DOI: 10.3969/j.issn.1000-1565.2025.03.008

Abstract

Served as a vital reservoir of resources for human, the ocean contains abundant water, mineral, and biological resources. However, the complexity and extremity of the deep-sea environment impose significant limitations on human exploration efforts. Consequently, developing deep-sea detection technologies, particularly artificial intelligence(AI)-assisted deep-sea vehicle exploration technologies, has become an urgent necessity for augmenting scientific knowledge and fostering sustainable resource utilization. Therefore, this paper systematically reviews the application of AI on several critical technologies of deep-sea vehicles, including underwater navigation and communication, underwater path planning and safe obstacle avoidance, underwater target detection and recognition, as well as fault diagnosis and fault-tolerant control mechanisms of underwater vehiches. Furthermore, it pinpoints the challenges and obstacles which AI-assisted deep-sea exploration are currently confronted with and analyzes prospective developmental trends for such technologies, thus providing a reference for future researches in this field.

Key words： artificial intelligence; deep-sea exploration; deep-sea vehicles; deep learning; neural network

参考文献

[1] 朱大奇,胡震.深海潜水器研究现状与展望[J].安徽师范大学学报(自然科学版), 2018, 41(3): 205-216. DOI: 10.14182/J.cnki.1001-2443.2018.03.001.
[2] 丁忠军,任玉刚,张奕,等.深海探测技术研发和展望[J].海洋开发与管理, 2019, 36(4): 71-77. DOI: 10.3969/j.issn.1005-9857.2019.04.016.
[3] 吴有生,赵羿羽,郎舒妍,等.智能无人潜水器技术发展研究[J].中国工程科学, 2020, 22(6): 26-31. DOI: 10.15302/J-SSCAE-2020.06.004.
[4] 张波波,Dongphil Chun,代学冬.国内外水下机器人研究前沿动态追踪:基于CiteSpace可视化分析[J].科学技术创新, 2023(24): 13-17. DOI: 10.3969/j.issn.1673-1328.2023.24.005.
[5] 周吉祥,刘慧敏,陆凯,等.深海ARV在海洋资源调查中的应用及展望[J].海洋地质前沿, 2024, 40(2): 93-102. DOI: 10.16028/j.1009-2722.2023.005.
[6] 黄琰,李岩,俞建成,等.AUV智能化现状与发展趋势[J].机器人, 2020(2): 215-231. DOI: 10.13973/j.cnki.robot.190392.
[7] 宋俊辉,严允,罗凌波,等.人工智能在深海机器人领域的应用研究[J].电子世界, 2019(6): 185-186. DOI: 10.19353/j.cnki.dzsj.2019.06.100.
[8] 汪顺亭,汪湛清.水下运载体导航技术[J].导航与控制, 2020, 19(4): 1-14. DOI: 10.3969/j.issn.1674-5558.2020.h4.001.
[9] 范刚,张亚,赵河明,等.水下机器人定位导航技术发展现状与分析[J].兵器装备工程学报, 2022, 43(3): 22-29. DOI: 10.11809/bqzbgcxb2022.03.003.
[10] ZHANG B B, JI D X, LIU S, et al. Autonomous Underwater Vehicle navigation: a review[J]. Ocean Eng, 2023, 273: 113861. DOI: 10.1016/j.oceaneng.2023.113861.
[11] 李昱,王俊雄.基于卷积神经网络的AUV水下识别算法设计与实现[J].舰船科学技术, 2021, 43(7): 155-158. DOI: 10.3404/j.issn.1672-7649.2021.04.031.
[12] NIU H Q, GONG Z X, OZANICH E, et al. Deep-learning source localization using multi-frequency magnitude-only data[J]. J Acoust Soc Am, 2019, 146(1): 211. DOI: 10.1121/1.5116016.
[13] 徐凤强,董鹏,王辉兵,等.基于水下机器人的海产品智能检测与自主抓取系统[J].北京航空航天大学学报, 2019, 45(12): 2393-2402. DOI: 10.13700/j.bh.1001-5965.2019.0377.
[14] HOU G C, SHAO Q, ZOU B, et al. A novel underwater simultaneous localization and mapping online algorithm based on neural network[J]. ISPRS Int J Geo Inf, 2019, 9(1): 5. DOI: 10.3390/ijgi9010005.
[15] CARLUCHO I, BAILEY M F, DE PAULA M, et al. Marine vehicles localization using grid cells for path integration[C] //OCEANS 2021: San Diego-Porto. San Diego, CA, USA. IEEE, 2021: 1-6. DOI: 10.23919/OCEANS44145.2021.9706050.
[16] 窦智,张彦敏,刘畅,等.AUV水下通信技术研究现状及发展趋势探讨[J].舰船科学技术, 2020, 42(2): 93-97. DOI: 10.3404/j.issn.1672-7649.2020.02.018.
[17] 陈友淦,许肖梅.人工智能技术在水声通信中的研究进展[J].哈尔滨工程大学学报, 2020, 41(10): 1536-1544. DOI: 10.11990/jheu.202007110.
[18] MAHMUTOGLU Y, TURK K, TUGCU E. Particle swarm optimization algorithm based decision feedback equalizer for underwater acoustic communication[C] //2016 39th International Conference on Telecommunications and Signal Processing(TSP). Vienna, Austria, IEEE, 2016: 153-156. DOI: 10.1109/TSP.2016.7760848.
[19] DESHPANDE A, SAKKARA S, SHESHADRI A. Underwater accoustic OFDM systems using deep neural network[C] //2022 3rd International Conference on Intelligent Engineering and Management(ICIEM), London, United Kingdom, IEEE, 2022: 195-200. DOI: 10.1109/ICIEM54221.2022.9853103.
[20] WANG C F, WANG Z H, SUN W S, et al. Reinforcement learning-based adaptive transmission in time-varying underwater acoustic channels[J]. IEEE Access, 2017, 6: 2541-2558. DOI: 10.1109/ACCESS.2017.2784239.
[21] KALAIARASU V, VISHNU H, MAHMOOD A, et al. Predicting underwater acoustic network variability using machine learning techniques[C] //OCEANS 2017 - Anchorage. Anchorage, AK, USA, IEEE, 2017: 1-7.
[22] 陈双双,顾师嘉,李娜娜,等.基于残差时序卷积网络的水声通信信号模式识别[J]. 无线电工程, 2024, 54(2): 473-482. DOI: 10.3969 / j.issn.1003-3106.2024.02.027.
[23] WANG Z Y, LI Y L, MA C P, et al. Path-following optimal control of autonomous underwater vehicle based on deep reinforcement learning[J]. Ocean Eng, 2023, 268: 113407. DOI: 10.1016/j.oceaneng.2022.113407.
[24] WANG Z, XIANG X B, DUAN Y, et al. Adversarial deep reinforcement learning based robust depth tracking control for underactuated autonomous underwater vehicle[J]. Eng Appl Artif Intell, 2024, 130: 107728. DOI: 10.1016/j.engappai.2023.107728.
[25] JIANG D, HUANG J, FANG Z, et al. Generative adversarial interactive imitation learning for path following of autonomous underwater vehicle[J]. Ocean Eng, 2022, 260: 111971. DOI: 10.1016/j.oceaneng.2022.111971.
[26] 韩恩全.基于深度学习的三维自主避障技术研究[J].数字海洋与水下攻防, 2021, 4(4): 264-268. DOI: 10.19838/j.issn.2096-5753.2021.04.002.
[27] BHOPALE P, KAZI F, SINGH N. Reinforcement learning based obstacle avoidance for autonomous underwater vehicle[J]. J Mar Sci Appl, 2019, 18(2): 228-238. DOI: 10.1007/s11804-019-00089-3.
[28] CHEN Q H, YANG J M, ZHAO W H, et al. AI-based dynamic avoidance in deep-sea mining[J]. Ocean Eng, 2024, 311: 118945. DOI: 10.1016/j.oceaneng.2024.118945.
[29] LU H M, LI Y J, ZHANG Y D, et al. Underwater optical image processing: a comprehensive review[J]. Mob Netw Appl, 2017, 22(6): 1204-1211. DOI: 10.1007/s11036-017-0863-4.
[30] 罗逸豪,曹翔,张钧陶,等.基于深度学习的水下光学图像超分辨率重建综述[J].数字海洋与水下攻防, 2023, 6(1): 17-33. DOI: 10.19838/j.issn.2096-5753.2023.01.003.
[31] 李思源,程磊,张婷,等.人工智能辅助的海洋立体观测与探测[J].数字海洋与水下攻防, 2023, 6(2):前插1, 120-132. DOI: 10.19838/j.issn.2096-5753.2023.02.001.
[32] HUANG H, ZHOU H, YANG X, et al. Faster R-CNN for marine organisms detection and recognition using data augmentation[J]. Neurocomputing, 2019, 337: 372-384. DOI: 10.1016/j.neucom.2019.01.084.
[33] 邹倩颖,陈晖阳,李永生,等.粒子群优化的深海图像暗边缘检测优化算法[J]. 应用科学学报, 2023, 41(1): 153-169. DOI: 10.3969/j.issn.0255-8297.2023.01.012.
[34] 叶赵兵,段先华,赵楚.改进YOLOv3-SPP水下目标检测研究[J].计算机工程与应用, 2023, 59(6): 231-240. DOI: 10.3778/j.issn.1002-8331.2204-0264.
[35] 李思聪,李然威.基于深度学习的深海会聚区目标分类方法[J].声学与电子工程, 2023(1): 18-23, 28. DOI: 10.3969/j.issn.2096-2657.2023.01.04.
[36] 陈悦,罗逸豪,李锦.基于多模态感知的水下目标检测应用构想[J].数字海洋与水下攻防, 2024, 7(3): 334-341. DOI: 10.19838/j.issn.2096-5753.2024.03.012.
[37] 王晨宇,刘礼文,刘罡,等.基于小样本条件下水下回波生成方法[J].水下无人系统学报, 2022, 30(5): 612-620. DOI: 10.11993/j.issn.2096-3920.202108015.
[38] 张铭钧.水下机器人故障诊断理论与技术[M].哈尔滨: 哈尔滨工程大学出版社, 2016.
[39] 王随平,张彤,宁小玲.基于集成神经网络的深海机器人故障诊断研究[J].计算机测量与控制, 2010, 18(4): 773-775. DOI: 10.16526/j.cnki.11-4762/tp.2010.04.060.
[40] MARICHAL G N, DEL CASTILLO M L, LÓPEZ J, et al. An artificial intelligence approach for gears diagnostics in AUVs[J]. Sensors, 2016, 16(4): 529. DOI: 10.3390/s16040529.
[41] RAANAN B Y, BELLINGHAM J, ZHANG Y W, et al. Detection of unanticipated faults for autonomous underwater vehicles using online topic models[J]. J Field Robot, 2018, 35(5): 705-716. DOI: 10.1002/rob.21771.
[42] BAGCI DAS D, BIRANT D. GASEL: genetic algorithm-supported ensemble learning for fault detection in autonomous underwater vehicles[J]. Ocean Eng, 2023, 272: 113844. DOI: 10.1016/j.oceaneng.2023.113844. (

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献