수중 영상을 이용한 수중 로봇의 그래프 기반 SLAM 실험

Abstract

This paper presents experiments on vision-based localization of an autonomous underwater vehicle (AUV) using graph-based simultaneous localization and mapping (SLAM). Through image processing techniques, relative ranges and bearings of landmarks are obtained. Landmark detection results and dead-reckoning data are used to a graph structure that represents a trajectory of AUV. The trajectory of AUV is optimized by a graph-based SLAM algorithm. Moreover, the performance of the graph-based SLAM is compared to results of an EKF-based SLAM.marks are obtained. Landmark detection results and dead-reckoning data are used to a graph structure that represents a trajectory of AUV. The trajectory of AUV is optimized by a graph-based SLAM algorithm. Moreover, the performance of the graph-based SLAM is compared to results of an EKF-based SLAM.