Accurate localization is an important part of successful autonomous driving. Recent studies suggest that when using map-based localization methods, the representation and layout of real-world phenomena within the prebuilt map is a source of error. To date, the investigations have been limited to 3D point clouds and normal distribution (ND) maps. This paper explores the potential of using OpenStreetMap (OSM) as a proxy to estimate vehicle localization error. Specifically, the experiment uses random forest regression to estimate mean 3D localization error from map matching using LiDAR scans and ND maps. Six map evaluation factors were defined for 2D geographic information in a vector format. Initial results for a 1.2 km path in Shinjuku, Tokyo, show that vehicle localization error can be estimated with 56.3% model prediction accuracy with two existing OSM data layers only. When OSM data quality issues (inconsistency and completeness) were addressed, the model prediction accuracy was improved to 73.1%.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Evaluating the Capability of OpenStreetMap for Estimating Vehicle Localization Error


    Contributors:


    Publication date :

    2019-10-01


    Size :

    657868 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Evaluating the Capability of OpenStreetMap for Estimating Vehicle Localization Error

    Wong, K / Javanmardi, E / Javanmardi, M et al. | BASE | 2019

    Free access

    Exploring OpenStreetMap Capability for Road Perception

    Zheng, Yang / Izzat, Izzat H. | IEEE | 2018


    EXPLORING OPENSTREETMAP CAPABILITY FOR ROAD PERCEPTION

    Zheng, Yang / Izzat, Izzat H. | British Library Conference Proceedings | 2018


    OpenStreetMap for traffic simulation

    Zilske, Michael / Neumann, Andreas / Nagel, Kai | DataCite | 2011

    Free access

    Packet Error Rate Based Validation Method for an OpenStreetMap Geometry-Based Channel Model

    Zelenbaba, Stefan / Rainer, Benjamin / Hofer, Markus et al. | IEEE | 2020