Learning to Anchor Visual Odometry: KAN-Based Pose Regression for Planetary Landing

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Luo, Xubo, Li, Zhaojin, Wan, Xue, Zhang, Wei, Shu, Leizheng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914311627079680
author Luo, Xubo
Li, Zhaojin
Wan, Xue
Zhang, Wei
Shu, Leizheng
author_facet Luo, Xubo
Li, Zhaojin
Wan, Xue
Zhang, Wei
Shu, Leizheng
contents Accurate and real-time 6-DoF localization is mission-critical for autonomous lunar landing, yet existing approaches remain limited: visual odometry (VO) drifts unboundedly, while map-based absolute localization fails in texture-sparse or low-light terrain. We introduce KANLoc, a monocular localization framework that tightly couples VO with a lightweight but robust absolute pose regressor. At its core is a Kolmogorov-Arnold Network (KAN) that learns the complex mapping from image features to map coordinates, producing sparse but highly reliable global pose anchors. These anchors are fused into a bundle adjustment framework, effectively canceling drift while retaining local motion precision. KANLoc delivers three key advances: (i) a KAN-based pose regressor that achieves high accuracy with remarkable parameter efficiency, (ii) a hybrid VO-absolute localization scheme that yields globally consistent real-time trajectories (>=15 FPS), and (iii) a tailored data augmentation strategy that improves robustness to sensor occlusion. On both realistic synthetic and real lunar landing datasets, KANLoc reduces average translation and rotation error by 32% and 45%, respectively, with per-trajectory gains of up to 45%/48%, outperforming strong baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2602_06968
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning to Anchor Visual Odometry: KAN-Based Pose Regression for Planetary Landing
Luo, Xubo
Li, Zhaojin
Wan, Xue
Zhang, Wei
Shu, Leizheng
Robotics
Computer Vision and Pattern Recognition
Accurate and real-time 6-DoF localization is mission-critical for autonomous lunar landing, yet existing approaches remain limited: visual odometry (VO) drifts unboundedly, while map-based absolute localization fails in texture-sparse or low-light terrain. We introduce KANLoc, a monocular localization framework that tightly couples VO with a lightweight but robust absolute pose regressor. At its core is a Kolmogorov-Arnold Network (KAN) that learns the complex mapping from image features to map coordinates, producing sparse but highly reliable global pose anchors. These anchors are fused into a bundle adjustment framework, effectively canceling drift while retaining local motion precision. KANLoc delivers three key advances: (i) a KAN-based pose regressor that achieves high accuracy with remarkable parameter efficiency, (ii) a hybrid VO-absolute localization scheme that yields globally consistent real-time trajectories (>=15 FPS), and (iii) a tailored data augmentation strategy that improves robustness to sensor occlusion. On both realistic synthetic and real lunar landing datasets, KANLoc reduces average translation and rotation error by 32% and 45%, respectively, with per-trajectory gains of up to 45%/48%, outperforming strong baselines.
title Learning to Anchor Visual Odometry: KAN-Based Pose Regression for Planetary Landing
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.06968