단일 카메라를 이용한 수중로봇의 도킹을 위한 자세 추정법

Abstract

Position Based Visual Servoing (PBVS) entails an accurate 3D pose estimation procedure in order to find the desired position and orientation of the robot. In this paper, we propose a complete vision based pose estimation method for the autonomous underwater docking problem. Our method finds the homography relation between the pattern coordinate frame and camera coordinate frame. Each homography is used for estimating the pose of the robot so as to determine the optimal path or sequence of the docking task. The proposed method is validated through real image data set, and the estimated orientation angles were compared against the corresponding IMU data. We have achieved promising results, and these results are quantitatively reported in the paper.