Cross-Level Degeneracy Perception for Robust LiDAR Localization

This work-in-progress extends LIO-SAM with cross-level degeneracy per-ception (CLDP). Geometric and scan-matching weak directions are jointly verifiedand temporally filtered into three reliability states that regulate directional dampingand LiDAR-factor covariance. Tests on five vehicle and two GEODE sequencesshow reduced drift, including a tunnel2 RMSE reduction from 17.01 to 7.29 magainst its best baseline. Additional independent diagnostics examine the relationbetween scene normals and runtime registration information.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-08
DOI
https://doi.org/10.5281/zenodo.24053196
Primary Topic
Robotics and Sensor-Based Localization
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Cross-Level Degeneracy Perception for Robust LiDAR Localization

Yang Sun, Xiaolin Meng, qing wang
Zenodo (CERN European Organization for Nuclear Research)
Robotics and Sensor-Based Localization
article

Cross-Level Degeneracy Perception for Robust LiDAR Localization

Yang Sun, Xiaolin Meng, qing wang
article en

Abstract

This work-in-progress extends LIO-SAM with cross-level degeneracy per-ception (CLDP). Geometric and scan-matching weak directions are jointly verifiedand temporally filtered into three reliability states that regulate directional dampingand LiDAR-factor covariance. Tests on five vehicle and two GEODE sequencesshow reduced drift, including a tunnel2 RMSE reduction from 17.01 to 7.29 magainst its best baseline. Additional independent diagnostics examine the relationbetween scene normals and runtime registration information.

Zenodo (CERN European Organization for Nuclear Research)
Southeast University (CN)
Robotics and Sensor-Based Localization
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon