DRIP: Discriminative Rotation-Invariant Pole Landmark Descriptor for 3D LiDAR Localization
This work addresses robot self-localization by improving landmark discriminability, though it is incremental as it builds on existing pole-based methods.
The paper tackles the problem of enhancing discriminability in pole-like landmarks for 3D LiDAR-based robot self-localization by including surrounding local regions and using a rotation-invariant CNN, resulting in improved performance in a state-of-the-art framework as demonstrated on the NCLT dataset.
In 3D LiDAR-based robot self-localization, pole-like landmarks are gaining popularity as lightweight and discriminative landmarks. This work introduces a novel approach called "discriminative rotation-invariant poles," which enhances the discriminability of pole-like landmarks while maintaining their lightweight nature. Unlike conventional methods that model a pole landmark as a 3D line segment perpendicular to the ground, we propose a simple yet powerful approach that includes not only the line segment's main body but also its surrounding local region of interest (ROI) as part of the pole landmark. Specifically, we describe the appearance, geometry, and semantic features within this ROI to improve the discriminability of the pole landmark. Since such pole landmarks are no longer rotation-invariant, we introduce a novel rotation-invariant convolutional neural network that automatically and efficiently extracts rotation-invariant features from input point clouds for recognition. Furthermore, we train a pole dictionary through unsupervised learning and use it to compress poles into compact pole words, thereby significantly reducing real-time costs while maintaining optimal self-localization performance. Monte Carlo localization experiments using publicly available NCLT dataset demonstrate that the proposed method improves a state-of-the-art pole-based localization framework.