Geo-Localization Based on Dynamically Weighted Factor-Graph
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/142740
Título: | Geo-Localization Based on Dynamically Weighted Factor-Graph |
---|---|
Autor/es: | Muñoz-Bañón, Miguel Á. | Olivas, Alejandro | Velasco, Edison P. | Candelas-Herías, Francisco A. | Torres, Fernando |
Grupo/s de investigación o GITE: | Automática, Robótica y Visión Artificial |
Centro, Departamento o Servicio: | Universidad de Alicante. Departamento de Física, Ingeniería de Sistemas y Teoría de la Señal | Universidad de Alicante. Instituto Universitario de Investigación Informática |
Palabras clave: | Geo-localization | Localization | Cross-view | Factor-graph | Autonomous vehicle navigation |
Fecha de publicación: | 2-may-2024 |
Editor: | IEEE |
Cita bibliográfica: | IEEE Robotics and Automation Letters. 2024, 9(6): 5599-5606. https://doi.org/10.1109/LRA.2024.3396055 |
Resumen: | Feature-based geo-localization relies on associating features extracted from aerial imagery with those detected by the vehicle's sensors. This requires that the type of landmarks must be observable from both sources. This lack of variety of feature types generates poor representations that lead to outliers and deviations produced by ambiguities and lack of detections, respectively. To mitigate these drawbacks, in this letter, we present a dynamically weighted factor graph model for the vehicle's trajectory estimation. The weight adjustment in this implementation depends on information quantification in the detections performed using a LiDAR sensor. Also, a prior (GNSS-based) error estimation is included in the model. Then, when the representation becomes ambiguous or sparse, the weights are dynamically adjusted to rely on the corrected prior trajectory, mitigating outliers and deviations in this way. We compare our method against state-of-the-art geo-localization ones in a challenging and ambiguous environment, where we also cause detection losses. We demonstrate mitigation of the mentioned drawbacks where the other methods fail. |
Patrocinador/es: | This work was supported in part by Regional Valencian Community Government and the European Union under Project PROMETEO/2021/075 and in part by Spanish Government under Grant PRE2019-088069, Grant PRE2022-101680, and Project PID2021-122685OB-I00. |
URI: | http://hdl.handle.net/10045/142740 |
ISSN: | 2377-3766 |
DOI: | 10.1109/LRA.2024.3396055 |
Idioma: | eng |
Tipo: | info:eu-repo/semantics/article |
Derechos: | © 2024 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission |
Revisión científica: | si |
Versión del editor: | https://doi.org/10.1109/LRA.2024.3396055 |
Aparece en las colecciones: | INV - AUROVA - Artículos de Revistas |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
Munoz-Banon_etal_2024_IEEE-RAL_final.pdf | Versión final (acceso restringido) | 1,77 MB | Adobe PDF | Abrir Solicitar una copia |
Munoz-Banon_etal_2024_IEEE-RAL_accepted.pdf | Accepted Manuscript (acceso abierto) | 4,72 MB | Adobe PDF | Abrir Vista previa |
Todos los documentos en RUA están protegidos por derechos de autor. Algunos derechos reservados.