Research

Paper

TESTING March 05, 2026

Loop Closure via Maximal Cliques in 3D LiDAR-Based SLAM

Authors

Javier Laserna, Saurabh Gupta, Oscar Martinez Mozos, Cyrill Stachniss, Pablo San Segundo

Abstract

Reliable loop closure detection remains a critical challenge in 3D LiDAR-based SLAM, especially under sensor noise, environmental ambiguity, and viewpoint variation conditions. RANSAC is often used in the context of loop closures for geometric model fitting in the presence of outliers. However, this approach may fail, leading to map inconsistency. We introduce a novel deterministic algorithm, CliReg, for loop closure validation that replaces RANSAC verification with a maximal clique search over a compatibility graph of feature correspondences. This formulation avoids random sampling and increases robustness in the presence of noise and outliers. We integrated our approach into a real- time pipeline employing binary 3D descriptors and a Hamming distance embedding binary search tree-based matching. We evaluated it on multiple real-world datasets featuring diverse LiDAR sensors. The results demonstrate that our proposed technique consistently achieves a lower pose error and more reliable loop closures than RANSAC, especially in sparse or ambiguous conditions. Additional experiments on 2D projection-based maps confirm its generality across spatial domains, making our approach a robust and efficient alternative for loop closure detection.

Metadata

arXiv ID: 2603.05397
Provider: ARXIV
Primary Category: cs.RO
Published: 2026-03-05
Fetched: 2026-03-06 14:20

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.05397v1</id>\n    <title>Loop Closure via Maximal Cliques in 3D LiDAR-Based SLAM</title>\n    <updated>2026-03-05T17:24:44Z</updated>\n    <link href='https://arxiv.org/abs/2603.05397v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.05397v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Reliable loop closure detection remains a critical challenge in 3D LiDAR-based SLAM, especially under sensor noise, environmental ambiguity, and viewpoint variation conditions. RANSAC is often used in the context of loop closures for geometric model fitting in the presence of outliers. However, this approach may fail, leading to map inconsistency. We introduce a novel deterministic algorithm, CliReg, for loop closure validation that replaces RANSAC verification with a maximal clique search over a compatibility graph of feature correspondences. This formulation avoids random sampling and increases robustness in the presence of noise and outliers. We integrated our approach into a real- time pipeline employing binary 3D descriptors and a Hamming distance embedding binary search tree-based matching. We evaluated it on multiple real-world datasets featuring diverse LiDAR sensors. The results demonstrate that our proposed technique consistently achieves a lower pose error and more reliable loop closures than RANSAC, especially in sparse or ambiguous conditions. Additional experiments on 2D projection-based maps confirm its generality across spatial domains, making our approach a robust and efficient alternative for loop closure detection.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.RO'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-05T17:24:44Z</published>\n    <arxiv:comment>Accepted in the 2025 European Conference on Mobile Robots (ECMR). This is the author's version of the work</arxiv:comment>\n    <arxiv:primary_category term='cs.RO'/>\n    <author>\n      <name>Javier Laserna</name>\n    </author>\n    <author>\n      <name>Saurabh Gupta</name>\n    </author>\n    <author>\n      <name>Oscar Martinez Mozos</name>\n    </author>\n    <author>\n      <name>Cyrill Stachniss</name>\n    </author>\n    <author>\n      <name>Pablo San Segundo</name>\n    </author>\n    <arxiv:doi>10.1109/ECMR65884.2025.11163179</arxiv:doi>\n    <link href='https://doi.org/10.1109/ECMR65884.2025.11163179' rel='related' title='doi'/>\n  </entry>"
}