SuperLoc: The Key to Robust LiDAR-Inertial Localization Lies in Predicting Alignment Risks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Shibo, Zhu, Honghao, Gao, Yuanjun, Kim, Beomsoo, Qiu, Yuheng, Johnson, Aaron M., Scherer, Sebastian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908287930204160
author Zhao, Shibo
Zhu, Honghao
Gao, Yuanjun
Kim, Beomsoo
Qiu, Yuheng
Johnson, Aaron M.
Scherer, Sebastian
author_facet Zhao, Shibo
Zhu, Honghao
Gao, Yuanjun
Kim, Beomsoo
Qiu, Yuheng
Johnson, Aaron M.
Scherer, Sebastian
contents Map-based LiDAR localization, while widely used in autonomous systems, faces significant challenges in degraded environments due to lacking distinct geometric features. This paper introduces SuperLoc, a robust LiDAR localization package that addresses key limitations in existing methods. SuperLoc features a novel predictive alignment risk assessment technique, enabling early detection and mitigation of potential failures before optimization. This approach significantly improves performance in challenging scenarios such as corridors, tunnels, and caves. Unlike existing degeneracy mitigation algorithms that rely on post-optimization analysis and heuristic thresholds, SuperLoc evaluates the localizability of raw sensor measurements. Experimental results demonstrate significant performance improvements over state-of-the-art methods across various degraded environments. Our approach achieves a 54% increase in accuracy and exhibits the highest robustness. To facilitate further research, we release our implementation along with datasets from eight challenging scenarios
format Preprint
id arxiv_https___arxiv_org_abs_2412_02901
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SuperLoc: The Key to Robust LiDAR-Inertial Localization Lies in Predicting Alignment Risks
Zhao, Shibo
Zhu, Honghao
Gao, Yuanjun
Kim, Beomsoo
Qiu, Yuheng
Johnson, Aaron M.
Scherer, Sebastian
Robotics
Map-based LiDAR localization, while widely used in autonomous systems, faces significant challenges in degraded environments due to lacking distinct geometric features. This paper introduces SuperLoc, a robust LiDAR localization package that addresses key limitations in existing methods. SuperLoc features a novel predictive alignment risk assessment technique, enabling early detection and mitigation of potential failures before optimization. This approach significantly improves performance in challenging scenarios such as corridors, tunnels, and caves. Unlike existing degeneracy mitigation algorithms that rely on post-optimization analysis and heuristic thresholds, SuperLoc evaluates the localizability of raw sensor measurements. Experimental results demonstrate significant performance improvements over state-of-the-art methods across various degraded environments. Our approach achieves a 54% increase in accuracy and exhibits the highest robustness. To facilitate further research, we release our implementation along with datasets from eight challenging scenarios
title SuperLoc: The Key to Robust LiDAR-Inertial Localization Lies in Predicting Alignment Risks
topic Robotics
url https://arxiv.org/abs/2412.02901