Evaluating the Capability of OpenStreetMap for Estimating Vehicle Localization Error

Kelvin Wong1, Ehsan Javanmardi1, Mahdi Javanmardi1, Yanlei Gu2, Shunsuke Kamijo1

  • 1The University of Tokyo
  • 2Ritsumeikan University


11:30 - 11:45 | Mon 28 October | Crystal Room II | MoC-T6.3

Session: Regular Session on Data Management and Geographic Information Systems (I)

Category: Regular Session


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%.