| 258 | 5 | 95 |
| 下载次数 | 被引频次 | 阅读次数 |
针对水下机器人自主作业安全性态势评估的问题，本文提出一种基于图像的水下环境安全性评估方法。通过单目摄像机采集图像，提取图像中环境物体与作业主体距离、水下物体运动状况和海底地质复杂度等环境要素信息，实现信息融合获得态势评估特征，构建态势评估模型，并对评估结果进行等级量化，得到海洋环境安全状态。此外，为了提高环境态势评估的计算效率，本文运用图像金字塔和四叉树对态势评估算法进行优化。实验表明，态势评估算法能够快速、准确地判断水下环境是否适宜开展自主作业，为精细化水下自主作业提供服务。
Abstract：The complex marine environment makes underwater autonomous operations face many challenges. Underwater robots need to conduct situation assessments of the marine environment to improve the accuracy of autonomous decision-making. Aiming at the problem of autonomous operation safety situation assessment of underwater robots, this paper proposes an image-based underwater environment safety assessment method. The monocular camera is used to collect images, extract the environmental element information such as the distance between the environmental objects and the main body of the operation, the motion status of the underwater objects, and the complexity of the seabed geology, and realize the information fusion to obtain the situation assessment features, build the situation assessment model, and analyze the assessment results. Level quantification to obtain marine environmental safety status indicators. In addition, to improve the calculation efficiency of environmental situation assessment, this paper uses image pyramid and quadtree to optimize the situation assessment algorithm. Experiments show that the situation assessment algorithm can quickly and accurately judge whether the underwater environment is suitable for autonomous operations, provide services for refined underwater autonomous operations, and play an important role in supporting ocean development.
[1] Siv■ev S,Coleman J,Omerdi■,et al.Underwater manipulators:A review[J].Ocean Engineering,2018,163:431-450.
[2] 李硕，刘健，徐会希，等.我国深海自主水下机器人的研究现[J].中国科学：信息科学，2018,48(9):1152-1164.Li S,Liu J,Xu H X,et al.Research on deep-sea autonomout under water vehicle in China[J].Science China Information Science,2018,48(9):1152 -1164.
[3] Wynn R B,Huvenne V A I,Le Bas T P,et al.Autonomous underwater vehicles (AUVs):Their past,present and future contributions to the advancement of marine geoscience[J].Marine Geo-logy,2014,352:451-468.
[4] 黄琰，李岩，俞建成，等.AUV智能化现状与发展趋势[J].机器人，2020,42(2):215-231.Huang Y,Li Y,Yu J C,et al.Current situation and development trend of AUV intelligence[J].Robot,2020,42(2):215-231.
[5] Azarewicz J,Fala G,Heithecker C.Template-based multi-agent plan recognition for tactical situation assessment[C]//Proceedings The Fifth Conference on Artificial Intelligence Applications.[s.l.]:IEEE Computer Society,1989:247-248.
[6] Morales C,Moral S.Modeling aircrew information management for estimation of situational awareness using dynamic Bayesian networks[J].Simulation Modelling Practice and Theory,2016,65:93-103.
[7] 何艳侠，尹慧琳，夏鹏飞.基于环境态势评估的智能车自主变道决策机制[J].汽车工程，2018,40(9):1048-1053.He Y X,Yin H L,Xia P F.Autonomous lane change decision mechanism of intelligent vehicle based on environmental situation assessment[J].Automotive Engineering,2018,40(9):1048-1053.
[8] Li M,Cao H,Song X,et al.Shared control driver assistance system based on driving intention and situation assessment[J].IEEE Transactions on Industrial Informatics,2018,14(11):4982-4994.
[9] 姜龙亭，寇雅楠，王栋，等.基于空战环境认知的态势评估[J].电子测量与仪器学报，2019,33(10):66-72.Jiang L T,Kou Y N,Wang D,et al.Situation assessment based on air combat environment auareness[J].Journal of Electronic Measurement and Instrument,2019,33(10):66-72.
[10] 丁华东，许华虎，段然，等.基于贝叶斯方法的网络安全态势感知模型[J].计算机工程，2020,46(6):130-135.Ding H D,Xu H H,Duan R,et al.Network security situation awareness model based on bayesian method[J].Computer Engineering,2020,46(6):130-135.
[11] Zhang Y,Lü R,Cai Y.Missile-target situation assessment model based on reinforcement learning[J].Journal of Shanghai Jiaotong University (Science),2020,25(5):561-568.
[12] Yang H,Zeng R,Xu G,et al.A network security situation assessment method based on adversarial deep learning[J].Applied Soft Computing,2021,102:107096.
[13] 高云，殷波，魏志强，等.动态不确定环境下机器人在线实时路径规划[J].中国海洋大学学报(自然科学版),2013,43(12):106-110.Gao Y,Yin B,Wei Z Q,et al.On-line realtime path planning for underwater vehicle in dynamic uncertain environment[J].Periodical of Ocean University of China,2013,43(12):106-110.
[14] Zhu D Q,Li W C,Yan M Z.Map building for underwater vehicle based on DS information fusion algorithm[J].System Simulation Technology,2012,8(3):181-186.
[15] 莫军，田亚龙.海洋环境对水下航行安全影响的综合评估[J].舰船科学技术，2012,34(10):89-93.Mo J,Tian Y L.Comprehensive evaluation of the impact of marine environment on underwater navigation safety[J].Ship Science and Technology,2012,34(10):89-93.
[16] Zhao Y,Jia R,Liu C.An evaluation method of underwater ocean environment safety situation based on DS evidence theory[J].Advances in Meteorology,2015(1):1-8.
[17] Snidaro L,Visentini I,Bryan K.Fusing uncertain knowledge and evidence for maritime situational awareness via Markov Logic Networks[J].Information Fusion,2015,21:159-172.
[18] 么洪飞，王宏健，王莹，等.基于遗传算法DDBN参数学习的UUV威胁评估[J].哈尔滨工程大学学报，2018,39(12):1972-1978.Yao H F,Wang H J,Wang Y,et al.UUV threat assessment based on genetic algorithm DDBN parameter learning[J].Journal of Harbin Engineering University,2018,39(12):1972-1978.
[19] 黄钦龙，刘忠，夏家伟.海上近岸目标威胁评估模型[J].指挥控制与仿真，2019,41(5):21-26.Huang Q L,Liu Z,Xia J W.Moritime and coastal target threat assessment model[J].Command Control & Simulation,2019,41(5):21-26.
[20] Lang K,Si D,Ma Z.A novel method of emergency situation evaluation for deep-sea based on bayesian network[J].IEEE Access,2020,8:215863-215873.
[21] Endsley M R.Toward a theory of situation awareness in dynamic systems[J].Human Factors,1995,37(1):32-64.
[22] 宋巍，朱孟飞，张明华，等.基于深度学习的单目深度估计技术综述[J].中国图象图形报，2022,27(2):292-328.Song W,Zhu M F,Zhang M H,et al.A review of monocular depth technology based on deep learning[J].Chinese Journal of Image and Graphics,202,27(2):292-328.
[23] Jaffe J S.Computer modeling and the design of optimal underwater imaging systems[J].IEEE Journal of Oceanic Engineering,1990,15(2):101-111.
[24] 邵绪强，杨艳，刘艺林.流体运动估计光流算法研究综述[J].中国图象图形学报，2021,26(2):355-367.Shao X Q,Yang Y,Liu Y L.Review of optical flow algorithms for fluid motion estimation[J].Journal of Image and Graphics,201,26(2):355-367.
[25] Peng Y T,Cosman P C.Underwater image restoration based on image blurriness and light absorption[J].IEEE Transactions on Image Processing,2017,26(4):1579-1594.
[26] Carlevaris-Bianco N,Mohan A,Eustice R M.Initial results in underwater single image dehazing[C]//Oceans 2010 Mts.[s.l.]:IEEE Seattle.IEEE,2010:1-8.
基本信息:
DOI：10.16441/j.cnki.hdxb.20220332
中图分类号:TP242
引用信息:
[1]胡文杰,王楠,续林刚,等.面向水下自主作业的环境安全性态势评估[J].中国海洋大学学报(自然科学版),2024,54(02):154-162.DOI:10.16441/j.cnki.hdxb.20220332.
基金信息:
国家自然科学基金项目(U2006228,61703381)资助~~
2022-07-04
2022
2022-08-23
2022-09-16
2022
1
2024-01-16
2024-01-16