Recently, the vehicle localization has become a major problem in the field of intelligent transportation systems (ITS). Modern vehicles support multiple systems for localization, such as Global Positioning System (GPS), Inertial Measurement Unit (IMU), lidar, and video feed. However, the problem of merging data from different sources for reducing errors remains challenging. This problem becomes increasingly hard if we use data with high uncertainty — for example, crowdsourced environmental features. Such data can provide invaluable information, especially when other data sources, such as GPS, are not available. Unfortunately, using it for vehicle localization requires great care, as crowdsourced data can be very noisy and imprecise. In this paper we present a Bayesian approach for sensor fusion, and use it to improve vehicle localization using crowdsourced data of traffic sign positions. We show that this method offers noticeable improvements (error reduction by 8.2%) compared to using GNSS and IMU only, and is comparable to the use of precise traffic signs positions —which are superior to crowdsourced positions, but very hard to obtain at scale.
Bayesian Framework for Vehicle Localization Using Crowdsourced Data
2018-06-01
1690009 byte
Conference paper
Electronic Resource
English
BAYESIAN FRAMEWORK FOR VEHICLE LOCALIZATION USING CROWDSOURCED DATA
British Library Conference Proceedings | 2018
|Pose-graph based Crowdsourced Mapping Framework
IEEE | 2020
|Mapping ridership using crowdsourced cycling data
Online Contents | 2016
|