基于视觉的AUV末端回收导引方法研究  

Research on AUV Terminal Recovery Guiding Method Based on Vision

作　　者：普勇博 齐向东 张海龙[1] 张涛[1] PU Yongbo;QI Xiangdong;ZHANG Hailong;ZHANG Tao(Key Laboratory of Instrumental Science and Dynamic Testing,Ministry of Education,North University of China,Taiyuan 030051,China)

机构地区：[1]中北大学仪器科学与动态测试教育部重点实验室,太原030051

出　　处：《计算机测量与控制》2024年第9期299-306,共8页Computer Measurement &Control

基　　金：水声对抗技术国防科技重点实验室基金项目(2023JCJQLB3302);山西省科技创新人才团队专项资助(202304051001030)。

摘　　要：水下自主无人潜航器(AUV,autonomous underwater vehicle)由于其独特的高速、低阻、低噪等优势,是如今探索海洋的有力依托;作为自主式机器人,AUV如何自行导航回收至对接站是研究中的重要环节;依托于实验室独创的四桨无舵矢量推进型AUV,通过改进Canny边缘检测,采用自适应阈值方法动态调整轮廓,在阈值最优时采用最小外接圆方法确定圆心;经Unity3D仿真和水池试验可知,该方法简单实用,鲁棒性强,且相比于传统的AUV形式以及传统的图像识别方法,该新型AUV在基于单目视觉的自适应阈值分割检测方法下,水下末端导引对接精度(优于20 cm)和对接成功率(大于80%)上均得到了大幅度的提高,在实际应用中对AUV能源补给、数据下载/上传、设备检修等具有重要的应用价值。An autonomous underwater vehicle(AUV)is an invaluable tool for exploring the ocean due to its unique advantages of high speed,low drag,and minimal acoustic signature.As an autonomous robot,it is an important research part for the AUV how to autonomously navigate and recover to the docking station.Based on the innovative four-paddle rudderless vector propellant AUV in the laboratory,through improving the Canny edge detection,an adaptive threshold method is used to dynamically adjust the entire contour;The minimum circumferential circle method is used to determine the circle center when the threshold is optimal.Through the Unity3D simulation and pool testing,this approach has the advantages of simple,practical,and strong robustness.Compared with traditional AUV designs and conventional image recognition methods,this novel AUV can effectively employ the adaptive threshold segmentation detection method based on monocular vision,which greatly improves the underwater terminal guidance docking accuracy of better than 20 cm as well as docking success rate of exceeding 80%.In practical applications,it is of great significance for AUV energy supply management,data upload/download,and equipment maintenance.

关 键 词：新型AUV 回收对接 Unity3D仿真 自适应阈值 单目视觉 图像处理 

分 类 号：U674[交通运输工程—船舶及航道工程] TP242[交通运输工程—船舶与海洋工程]