Loop detection for 3D LiDAR SLAM using segment-group matching

Abstract

Three-dimensional (3D) maps are indispensable for autonomous robot navigation in outdoor environments. Loop closure, which is a key technology in robotic mapping, is essential for creating consistent maps. This paper proposes an efficient method of loop detection for 3D-mapping. The proposed method detects loop constraints by estimating robot poses in revisited places using point-cloud registration. A difficulty in the registration is a large set of 3D points obtained by laser sensors, which requires a long processing time. To reduce the processing time, the proposed method employs a coarse-to-fine approach. Coarse estimation is performed using planes, lines, and balls instead of 3D points, and reduces the hypothesized loop constraints using geometric constraints between the segments. Subsequently, fine estimation is performed using the iterative closest points (ICP) algorithm and 3D points. Another difficulty is the precision of loop detection. To increase the precision, the proposed method employs robustification techniques such as outlier removal in the registration, combination of feature-based and pose-based methods, and robust pose adjustment. Experiments using large-scale datasets show that the proposed method realizes realtime loop detection in a variety of outdoor environments including cities, parks, and forest areas.