When and Where Localization Fails: An Analysis of the Iterative Closest Point in Evolving Environment

TL;DR

This paper evaluates the performance of ICP variants for short-term lidar-based localization in dynamic outdoor environments, highlighting the importance of local geometry and environmental changes.

Contribution

It introduces a high-resolution, multi-temporal dataset for evaluating short-term localization and compares ICP Point-to-Point and Point-to-Plane methods in evolving outdoor scenes.

Findings

Point-to-Plane ICP provides more stable registration than Point-to-Point.

Sparse features and dense vegetation reduce ICP accuracy.

Environmental variability significantly impacts localization success.

Abstract

Robust relocalization in dynamic outdoor environments remains a key challenge for autonomous systems relying on 3D lidar. While long-term localization has been widely studied, short-term environmental changes, occurring over days or weeks, remain underexplored despite their practical significance. To address this gap, we present a highresolution, short-term multi-temporal dataset collected weekly from February to April 2025 across natural and semi-urban settings. Each session includes high-density point cloud maps, 360 deg panoramic images, and trajectory data. Projected lidar scans, derived from the point cloud maps and modeled with sensor-accurate occlusions, are used to evaluate alignment accuracy against the ground truth using two Iterative Closest Point (ICP) variants: Point-to-Point and Point-to-Plane. Results show that Point-to-Plane offers significantly more stable and accurate registration, particularly in areas with sparse features or dense vegetation. This study provides a structured dataset for evaluating short-term localization robustness, a reproducible framework for analyzing scan-to-map alignment under noise, and a comparative evaluation of ICP performance in evolving outdoor environments. Our analysis underscores how local geometry and environmental variability affect localization success, offering insights for designing more resilient robotic systems.