On the descriptive power of LiDAR intensity images for segment-based loop closing in 3-D SLAM
This work addresses loop closure reliability in SLAM for robotics, but it is incremental as it extends an existing method with a new neural network architecture.
The paper tackled the problem of improving loop closure detection in 3D SLAM by enhancing segment-based descriptors using LiDAR intensity images, resulting in more reliable loop closure detection as demonstrated on two public datasets.
We propose an extension to the segment-based global localization method for LiDAR SLAM using descriptors learned considering the visual context of the segments. A new architecture of the deep neural network is presented that learns the visual context acquired from synthetic LiDAR intensity images. This approach allows a single multi-beam LiDAR to produce rich and highly descriptive location signatures. The method is tested on two public datasets, demonstrating an improved descriptiveness of the new descriptors, and more reliable loop closure detection in SLAM. Attention analysis of the network is used to show the importance of focusing on the broader context rather than only on the 3-D segment.