Fusión de sensores para la localización robusta de vehículos autónomos en áreas urbanas
-
1
Universidad del País Vasco/Euskal Herriko Unibertsitatea
info
Universidad del País Vasco/Euskal Herriko Unibertsitatea
Lejona, España
Publisher: Universitat Jaume I ; Servizo de Publicacións ; Universidade da Coruña ; Comité Español de Automática
ISBN: 978-84-9749-804-3
Year of publication: 2021
Pages: 309-316
Congress: Jornadas de Automática (42. 2021. Castellón)
Type: Conference paper
Abstract
Localization in dense urban areas may be difficult, as GPS signal usually gets blocked by buildings or tunnels. Therefore, autonomous vehicles need to implement alternatives for those circumstances with a fault-tolerant localization structure. This is an area of great interest that most works address by combining duplicationcomparison techniques and the use of belief functions and alternative localization algorithms such as map-matching or visual odometry. This paper proposes a localization framework for dense urban areas that includes both a robust fault-tolerant algorithm capable of determining the reliability of every position estimation, and a computationally low demanding map matching algorithm as an accurate alternative localization strategy. Validation on simulation environment has proved that the proposed approach is functional.