Research on AUV Terminal Recovery Guiding Method Based on Vision
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 en-ergy supply management,data upload/download,and equipment maintenance.
万方数据
维普
