Mobile Robot Localization: a Modular, Odometry-Improving Approach

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mozzarelli, Luca, Cattaneo, Luca, Corno, Matteo, Savaresi, Sergio Matteo
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916168048050176
author Mozzarelli, Luca
Cattaneo, Luca
Corno, Matteo
Savaresi, Sergio Matteo
author_facet Mozzarelli, Luca
Cattaneo, Luca
Corno, Matteo
Savaresi, Sergio Matteo
contents Despite the number of works published in recent years, vehicle localization remains an open, challenging problem. While map-based localization and SLAM algorithms are getting better and better, they remain a single point of failure in typical localization pipelines. This paper proposes a modular localization architecture that fuses sensor measurements with the outputs of off-the-shelf localization algorithms. The fusion filter estimates model uncertainties to improve odometry in case absolute pose measurements are lost entirely. The architecture is validated experimentally on a real robot navigating autonomously proving a reduction of the position error of more than 90% with respect to the odometrical estimate without uncertainty estimation in a two-minute navigation period without position measurements.
format Preprint
id arxiv_https___arxiv_org_abs_2403_13452
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mobile Robot Localization: a Modular, Odometry-Improving Approach
Mozzarelli, Luca
Cattaneo, Luca
Corno, Matteo
Savaresi, Sergio Matteo
Robotics
Despite the number of works published in recent years, vehicle localization remains an open, challenging problem. While map-based localization and SLAM algorithms are getting better and better, they remain a single point of failure in typical localization pipelines. This paper proposes a modular localization architecture that fuses sensor measurements with the outputs of off-the-shelf localization algorithms. The fusion filter estimates model uncertainties to improve odometry in case absolute pose measurements are lost entirely. The architecture is validated experimentally on a real robot navigating autonomously proving a reduction of the position error of more than 90% with respect to the odometrical estimate without uncertainty estimation in a two-minute navigation period without position measurements.
title Mobile Robot Localization: a Modular, Odometry-Improving Approach
topic Robotics
url https://arxiv.org/abs/2403.13452