A Novel Loop Closure Detection Approach Using Simplified Structure for Low-Cost LiDAR

Abstract

Reducing the cumulative error is a crucial task in simultaneous localization and mapping (SLAM). Usually, Loop Closure Detection (LCD) is exploited to accomplish this work for SLAM and robot navigation. With a fast and accurate loop detection, it can significantly improve global localization stability and reduce mapping errors. However, the LCD task based on point cloud still has some problems, such as over-reliance on high-resolution sensors, and poor detection efficiency and accuracy. Therefore, in this paper, we propose a novel and fast global LCD method using a low-cost 16 beam Lidar based on “Simplified Structure”. Firstly, we extract the “Simplified Structure” from the indoor point cloud, classify them into two levels, and manage the “Simplified Structure” hierarchically according to its structure salience. The “Simplified Structure” has simple feature geometry and can be exploited to capture the indoor stable structures. Secondly, we analyze the point cloud registration suitability with a pre-match, and present a hierarchical matching strategy with multiple geometric constraints in Euclidean Space to match two scans. Finally, we construct a multi-state loop evaluation model for a multi-level structure to determine whether the two candidate scans are a loop. In fact, our method also provides a transformation for point cloud registration with “Simplified Structure” when a loop is detected successfully. Experiments are carried out on three types of indoor environment. A 16 beam Lidar is used to collect data. The experimental results demonstrate that our method can detect global loop closures efficiently and accurately. The average global LCD precision, accuracy and negative are approximately 0.90, 0.96, and 0.97, respectively.

Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey

“…The loop detection methods using a point-cloud-segmentation approach are based on shapes or objects recognition [ 75 , 76 , 77 , 78 , 79 , 80 ]. In such methods, segmentation is performed as a preprocessing step because a priori knowledge about location of objects, that are to be segmented during robot navigation, is needed.…”

Indoor Multi-Robot Cooperative Mapping Based on Geometric Features

“…Compared with the loop detection, the overlapped area detection contains more data without any rule to follow. [35] suggested that general large-scale buildings are consisted of corridors, lobbies, public foyers, and other areas. By analyzing the indoor environment characteristics, the building structure is mainly consisted of walls, corners, columns, and other building structures.…”

“…By analyzing the indoor environment characteristics, the building structure is mainly consisted of walls, corners, columns, and other building structures. A description method based on the simplified structure of the indoor point cloud is proposed by [35] to extract the salient features of the original point cloud. Inspired by the simplified structure loop detection, the 3D cooperative mapping method based on the geometric features of building structures is proposed.…”

Cost-effective Mapping of Mobile Robot Based on the Fusion of UWB and Short-range 2D LiDAR

“…The LiDAR loop closure-based edge between non-adjacent vertices is added to further constrain the pose during the second pose graph optimization after the first optimization. Studies show that loop closure detection is essential for graph optimization method [35]. In other words, the correct LiDAR loop closure detection can remove the cumulative error of the odometry, thereby obtaining a consistent map.…”