DB-LIO: Database-Driven LiDAR–Inertial Odometry for Memory-Bounded Persistent Mapping
Sensors · 12.05.2026 · 26 (10) · 3061
DOI: 10.3390/s26103061 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 12.05.2026. Verfasst von Hun-Hee Kim und 3 weiteren Autor:innen. Beteiligte Einrichtung: AI Application Research Center, Korea Electronics Technology Institute (KETI), Jeonju 54853, Republic of Korea. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Trade, Industry and Energy, Korea Forest Service, Korea Institute of Planning and Evaluation for Technology in Food, Agriculture, Forestry and Fisheries.
Abstract (Originalsprache)
This paper proposes DB-LIO (database-driven LiDAR-inertial odometry), a simultaneous localization and mapping (SLAM) system that addresses memory scalability challenges in extended autonomous operation. Existing LiDAR-SLAM systems accumulate keyframe history in memory, leading to O(N) growth and out-of-memory failures during extended operation. To overcome this limitation, DB-LIO introduces three core design elements. First, it proposes a spatially indexed keyframe management scheme that persistently stores keyframes in SQLite with R-Tree spatial indexing, enabling O(logN+k) spatial queries that tightly couple cache eviction with factor-graph optimization requirements—a design that ensures every keyframe potentially involved in the next optimization cycle resides in cache. Second, it presents a four-level memory bounding architecture—SLAM-engine keyframe trimming with transparent on-demand reloading, a DB-level least recently used (LRU) cache with a spatial active window, Scan Context descriptor pool bounding, and iSAM2 sliding window compaction with a sparse global anchor graph—that collectively bounds the dominant memory consumers to O(C). Third, the DB-based persistent storage enables a localization mode that can reload previously built maps—including full point clouds, six-degree-of-freedom poses, timestamps, and inter-keyframe relationships—and perform pose estimation using the stored map, which is particularly valuable for agricultural robots and other autonomous systems requiring map reuse. Experiments on a custom orchard dataset demonstrate an 81.9% reduction in memory usage compared with that of the in-memory baseline (2888 MB → 524 MB), while preserving equivalent trajectory accuracy (absolute trajectory error (ATE) root mean square error (RMSE) 0.305 ± 0.001 m vs. 0.296 m). Validation on the KITTI odometry benchmark confirms that the proposed localization mode generalizes across different LiDAR types (Livox Mid360, Velodyne HDL-64E) and environments (orchard, urban driving).
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- AI Application Research Center, Korea Electronics Technology Institute (KETI), Jeonju 54853, Republic of Korea.
- Division of Electronic Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea.
ORCID-Profile: Hun-Hee Kim, Ho-Hyun Kang, Dong-Hee Noh, Hea-Min Lee
Förderung
- Ministry of Trade, Industry and Energy
- Korea Forest Service
- Korea Institute of Planning and Evaluation for Technology in Food, Agriculture, Forestry and Fisheries
- Ministry of Trade, Industry & Energy
- Ministry of Agriculture, Food and Rural Affairs
Zitieren
APA
Kim, H. H., Kang, H. H., Noh, D. H., & Lee, H. M. (2026). DB-LIO: Database-Driven LiDAR–Inertial Odometry for Memory-Bounded Persistent Mapping. Sensors, 26(10), 3061. https://doi.org/10.3390/s26103061
Vancouver
Kim HH, Kang HH, Noh DH, Lee HM. DB-LIO: Database-Driven LiDAR–Inertial Odometry for Memory-Bounded Persistent Mapping. Sensors. 2026;26(10):3061. doi:10.3390/s26103061
BibTeX
@article{Kim2026,
author = {Kim, Hun-Hee and Kang, Ho-Hyun and Noh, Dong-Hee and Lee, Hea-Min},
title = {DB-LIO: Database-Driven LiDAR–Inertial Odometry for Memory-Bounded Persistent Mapping},
journal = {Sensors},
year = {2026},
volume = {26},
number = {10},
pages = {3061},
doi = {10.3390/s26103061}
}
EUVIMED