Pole-Image: A Self-Supervised Pole-Anchored Descriptor for Long-Term LiDAR Localization and Map Maintenance

TL;DR

To enable lifelong LiDAR-based localization and map maintenance, the paper introduces Pole-Image, a pole-centric canonical representation that encodes a pole landmark and its surrounding 3D structure as a 2D polar image. By decoupling easy pole detection from landmark identification and applying self-supervised contrastive learning, the method yields a lightweight 256-D descriptor that is robust to viewpoint change and sensitive to environmental changes. Evaluations on the IRIS dataset show that Pole-Image descriptors learned via contrastive learning outperform handcrafted baselines and supervised learning, with contrastive learning delivering the strongest retrieval performance. The approach promises improved long-term autonomy by enabling reliable self-localization and more sensitive map maintenance, and it can be integrated into an active-passive-SSL loop for continual improvement.

Abstract

Long-term autonomy for mobile robots requires both robust self-localization and reliable map maintenance. Conventional landmark-based methods face a fundamental trade-off between landmarks with high detectability but low distinctiveness (e.g., poles) and those with high distinctiveness but difficult stable detection (e.g., local point cloud structures). This work addresses the challenge of descriptively identifying a unique "signature" (local point cloud) by leveraging a detectable, high-precision "anchor" (like a pole). To solve this, we propose a novel canonical representation, "Pole-Image," as a hybrid method that uses poles as anchors to generate signatures from the surrounding 3D structure. Pole-Image represents a pole-like landmark and its surrounding environment, detected from a LiDAR point cloud, as a 2D polar coordinate image with the pole itself as the origin. This representation leverages the pole's nature as a high-precision reference point, explicitly encoding the "relative geometry" between the stable pole and the variable surrounding point cloud. The key advantage of pole landmarks is that "detection" is extremely easy. This ease of detection allows the robot to easily track the same pole, enabling the automatic and large-scale collection of diverse observational data (positive pairs). This data acquisition feasibility makes "Contrastive Learning (CL)" applicable. By applying CL, the model learns a viewpoint-invariant and highly discriminative descriptor. The contributions are twofold: 1) The descriptor overcomes perceptual aliasing, enabling robust self-localization. 2) The high-precision encoding enables high-sensitivity change detection, contributing to map maintenance.