SparseLoc: Sparse Open-Set Landmark-based Global Localization for Autonomous Navigation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Paul, Pranjal, Bhat, Vineeth, Salian, Tejas, Omama, Mohammad, Jatavallabhula, Krishna Murthy, Arulselvan, Naveen, Krishna, K. Madhava
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913961676374016
author Paul, Pranjal
Bhat, Vineeth
Salian, Tejas
Omama, Mohammad
Jatavallabhula, Krishna Murthy
Arulselvan, Naveen
Krishna, K. Madhava
author_facet Paul, Pranjal
Bhat, Vineeth
Salian, Tejas
Omama, Mohammad
Jatavallabhula, Krishna Murthy
Arulselvan, Naveen
Krishna, K. Madhava
contents Global localization is a critical problem in autonomous navigation, enabling precise positioning without reliance on GPS. Modern global localization techniques often depend on dense LiDAR maps, which, while precise, require extensive storage and computational resources. Recent approaches have explored alternative methods, such as sparse maps and learned features, but they suffer from poor robustness and generalization. We propose SparseLoc, a global localization framework that leverages vision-language foundation models to generate sparse, semantic-topometric maps in a zero-shot manner. It combines this map representation with a Monte Carlo localization scheme enhanced by a novel late optimization strategy, ensuring improved pose estimation. By constructing compact yet highly discriminative maps and refining localization through a carefully designed optimization schedule, SparseLoc overcomes the limitations of existing techniques, offering a more efficient and robust solution for global localization. Our system achieves over a 5X improvement in localization accuracy compared to existing sparse mapping techniques. Despite utilizing only 1/500th of the points of dense mapping methods, it achieves comparable performance, maintaining an average global localization error below 5m and 2 degrees on KITTI sequences.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23465
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SparseLoc: Sparse Open-Set Landmark-based Global Localization for Autonomous Navigation
Paul, Pranjal
Bhat, Vineeth
Salian, Tejas
Omama, Mohammad
Jatavallabhula, Krishna Murthy
Arulselvan, Naveen
Krishna, K. Madhava
Robotics
Global localization is a critical problem in autonomous navigation, enabling precise positioning without reliance on GPS. Modern global localization techniques often depend on dense LiDAR maps, which, while precise, require extensive storage and computational resources. Recent approaches have explored alternative methods, such as sparse maps and learned features, but they suffer from poor robustness and generalization. We propose SparseLoc, a global localization framework that leverages vision-language foundation models to generate sparse, semantic-topometric maps in a zero-shot manner. It combines this map representation with a Monte Carlo localization scheme enhanced by a novel late optimization strategy, ensuring improved pose estimation. By constructing compact yet highly discriminative maps and refining localization through a carefully designed optimization schedule, SparseLoc overcomes the limitations of existing techniques, offering a more efficient and robust solution for global localization. Our system achieves over a 5X improvement in localization accuracy compared to existing sparse mapping techniques. Despite utilizing only 1/500th of the points of dense mapping methods, it achieves comparable performance, maintaining an average global localization error below 5m and 2 degrees on KITTI sequences.
title SparseLoc: Sparse Open-Set Landmark-based Global Localization for Autonomous Navigation
topic Robotics
url https://arxiv.org/abs/2503.23465