Effectively Detecting Loop Closures using Point Cloud Density Maps

The ability to detect loop closures plays an essential role in any SLAM system. Loop closures allow correcting the drifting pose estimates from a sensor odometry pipeline. In this paper, we address the problem of effectively detecting loop closures in LiDAR SLAM systems in various environments with longer lengths of sequences and agnostic of the scanning pattern of the sensor. While many approaches for loop closures using 3D LiDAR sensors rely on individual scans, we propose the usage of local maps generated from locally consistent odometry estimates. Several recent approaches compute the maximum elevation map on a bird’s eye view projection of point clouds to compute feature descriptors. In contrast, we use a density image bird’s eye view representation, which is robust to viewpoint changes. The utilization of dense local maps allows us to reduce the complexity of features describing these maps, as well as the size of the database required to store these features over a long sequence. This yields a real-time application of our approach for a typical robotic 3D LiDAR sensor. We perform extensive experiments to evaluate our approach against other state-of-the-art approaches and show the benefits of our proposed approach.

Authors

• Saurabh Gupta
• Tiziano Guadagnino
• Benedikt Mersch
• Ignacio Vizzo
• Cyrill Stachniss

Keywords

• Point cloud compression
• Simultaneous localization and mapping
• Laser radar
• Three-dimensional displays
• Image coding
• Pipelines
• Image representation
• Density Map
• Point Cloud
• Loop Closure
• Loop Closure Detection
• Descriptive Characteristics
• Topographic Maps
• Local Map
• Pose Estimation
• Bird’s Eye
• Density Imaging
• Individual Scans
• Scan Pattern
• Viewpoint Changes
• Environmental Variables
• F1 Score
• Precision And Recall
• Feature Detection
• Number Of Scans
• Leaf Node
• Feature Matching
• Binary Tree
• Random Sample Consensus
• Voxel Grid
• Recall Score
• Local Reference Frame
• Hamming Distance
• Functional Database
• Consecutive Scans
• LiDAR Scans