Evaluating and Improving the Robustness of LiDAR Odometry and Localization Under Real-World Corruptions

TL;DR

This paper benchmarks the robustness of LiDAR odometry and localization under various real-world corruptions, revealing significant performance degradation and proposing detection and filtering strategies to improve resilience.

Contribution

It introduces the first comprehensive robustness benchmark for LiDAR pose estimation under synthetic corruptions and proposes effective detection and filtering methods to enhance robustness.

Findings

Odometry errors increase dramatically under corruptions, from 0.5% to over 80%.

Filtering restores odometry accuracy close to clean data levels.

Fine-tuning learning-based systems on corrupted data improves robustness and performance.

Abstract

LiDAR odometry and localization are two widely used and fundamental applications in robotic and autonomous driving systems. Although state-of-the-art (SOTA) systems achieve high accuracy on clean point clouds, their robustness to corrupted data remains largely unexplored. We present the first comprehensive benchmark to evaluate the robustness of LiDAR pose-estimation techniques under 18 realistic synthetic corruptions. Our results show that, under these corruptions, odometry position errors escalate from 0.5% to more than 80%, while localization performance stays consistently high. To address this sensitivity, we propose two complementary strategies. First, we design a lightweight detection-and-filter pipeline that classifies the point cloud corruption and applies a corresponding filter (e.g., bilateral filter for noise) to restore the point cloud quality. Our classifier accurately identifies each corruption type, and the filter effectively restores odometry accuracy to near-clean data levels. Second, for learning-based systems, we show that fine-tuning using the corrupted data substantially improves robustness across all tested corruptions and even boosts performance on clean point clouds on one data sequence.