Mr. Virgil: Learning Multi-robot Visual-range Relative Localization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Si, Li, Zhehan, Lu, Jiadong, Xiong, Rong, Cao, Yanjun, Wang, Yue
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914195030671360
author Wang, Si
Li, Zhehan
Lu, Jiadong
Xiong, Rong
Cao, Yanjun
Wang, Yue
author_facet Wang, Si
Li, Zhehan
Lu, Jiadong
Xiong, Rong
Cao, Yanjun
Wang, Yue
contents Ultra-wideband (UWB)-vision fusion localization has achieved extensive applications in the domain of multi-agent relative localization. The challenging matching problem between robots and visual detection renders existing methods highly dependent on identity-encoded hardware or delicate tuning algorithms. Overconfident yet erroneous matches may bring about irreversible damage to the localization system. To address this issue, we introduce Mr. Virgil, an end-to-end learning multi-robot visual-range relative localization framework, consisting of a graph neural network for data association between UWB rangings and visual detections, and a differentiable pose graph optimization (PGO) back-end. The graph-based front-end supplies robust matching results, accurate initial position predictions, and credible uncertainty estimates, which are subsequently integrated into the PGO back-end to elevate the accuracy of the final pose estimation. Additionally, a decentralized system is implemented for real-world applications. Experiments spanning varying robot numbers, simulation and real-world, occlusion and non-occlusion conditions showcase the stability and exactitude under various scenes compared to conventional methods. Our code is available at: https://github.com/HiOnes/Mr-Virgil.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10540
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mr. Virgil: Learning Multi-robot Visual-range Relative Localization
Wang, Si
Li, Zhehan
Lu, Jiadong
Xiong, Rong
Cao, Yanjun
Wang, Yue
Robotics
Ultra-wideband (UWB)-vision fusion localization has achieved extensive applications in the domain of multi-agent relative localization. The challenging matching problem between robots and visual detection renders existing methods highly dependent on identity-encoded hardware or delicate tuning algorithms. Overconfident yet erroneous matches may bring about irreversible damage to the localization system. To address this issue, we introduce Mr. Virgil, an end-to-end learning multi-robot visual-range relative localization framework, consisting of a graph neural network for data association between UWB rangings and visual detections, and a differentiable pose graph optimization (PGO) back-end. The graph-based front-end supplies robust matching results, accurate initial position predictions, and credible uncertainty estimates, which are subsequently integrated into the PGO back-end to elevate the accuracy of the final pose estimation. Additionally, a decentralized system is implemented for real-world applications. Experiments spanning varying robot numbers, simulation and real-world, occlusion and non-occlusion conditions showcase the stability and exactitude under various scenes compared to conventional methods. Our code is available at: https://github.com/HiOnes/Mr-Virgil.
title Mr. Virgil: Learning Multi-robot Visual-range Relative Localization
topic Robotics
url https://arxiv.org/abs/2512.10540