크레인 충돌 방지를 위한 특징 추출 기반의 SLAM 기법

Abstract

There is an increasing need for Simultaneous Localization and Mapping (SLAM) technology due to the recent demand for autonomous driving, metaverse, and augmented reality (AR) technologies. On industrial sites, demands for SLAM technologies that accurately estimate locations and generate precise maps of surrounding areas are becoming increasingly important for collision prevention between cranes. The research in this paper proposes a SLAM technology based on feature extraction techniques that create a precise map of the workspace in an industrial site by attaching a double-axis rotary Lidar to a tower crane. This configuration compensates for the limitation in single-axis rotary Lidar’s detection range. The double-axis rotary Lidar has a wider detection range than rotary Lidar, but the distribution of the collected data is irregular due to shaking and the difference in rotational speeds of the two motors in separate axes. SLAM techniques, including feature extraction and motion estimation suitable for these data characteristics, were introduced to aid in improving these data irregularities. Even when the SLAM algorithm operates accurately, the presence of afterimages from a dynamic object on the map can prevent effective collision performance and result in an inaccurate representation of the workspace. This paper explores an algorithm that effectively removes afterimages by scoring all the points collected by Lidar. The performance accuracy of the proposed SLAM method was evaluated by comparing the results of Mapping with those of conventional LOAM and G-ICP processes using data from attaching double-axis Lidar to the tower crane.