3차원 라이다 센서를 이용한 표지판 추출 및 고정밀 지도 매칭

Abstract

Recently, there has been a lot of research on localization of the autonomous vehicle. For better localization result, the system requires better feature extraction and map matching result. In this paper, we propose a feature extraction method using traffic signs and HD map matching to have better localization of the autonomous vehicle using a 3D LiDAR sensor. The map matching result can be utilized in the Monte Carlo Localization (MCL) and graph-based Simultaneous Localization and Mapping System (SLAM). We verified the proposed method in the city and inside the campus.