DRIP: Discriminative Rotation-Invariant Pole Landmark Descriptor for 3D LiDAR Localization

TL;DR

This paper introduces DRIP, a novel method for 3D LiDAR localization that uses discriminative, rotation-invariant pole landmarks with an enhanced local region, improving discriminability and efficiency.

Contribution

The paper proposes a new pole landmark descriptor that combines appearance, geometry, and semantics within a local region, along with a rotation-invariant CNN for recognition, and an unsupervised pole dictionary for efficiency.

Findings

Improves localization accuracy over state-of-the-art pole-based methods.

Reduces real-time computational costs through pole dictionary compression.

Demonstrates effectiveness on the NCLT dataset.

Abstract

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.