Terminology and Analysis of Map Deviations in Urban Domains: Towards Dependability for HD Maps in Automated Vehicles

A driving function relying on map data to operate is prone to failures that are due to deviations between the real world and the map data. Hence, we transfer the concept of dependability known from systems engineering to high-definition (HD) maps to allow for a system ensuring three major aspects of dependability: reliability, availability, and the safe use of map data within the vehicle. In this paper, we therefore define a coherent terminology in the field, particularly introducing necessary terms for describing and measuring map deviations. To substantiate our terminology, we present the results of a measurement campaign and analyze map deviations in an urban domain HD map after a period of 2 years. The results show that the analyzed map contains relatively few errors (0.07 / km) and no obvious persistent changes over the years but is subject to a comparatively high number of temporary changes (0.74 / km) rendering almost 9% of the map outdated.

[1]  Cyrill Stachniss,et al.  Localization with Sliding Window Factor Graphs on Third-Party Maps for Automated Driving , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[2]  A. Knoll,et al.  Online Map Validation for Autonomous Driving , 2019 .

[3]  Muhammed Oğuz TAŞ,et al.  Updating HD-Maps for Autonomous Transfer Vehicles in Smart Factories , 2018, 2018 6th International Conference on Control Engineering & Information Technology (CEIT).

[4]  Chris Urmson,et al.  Traffic light mapping and detection , 2011, 2011 IEEE International Conference on Robotics and Automation.

[5]  Michael R. M. Jenkin,et al.  Map Validation and Self-location in a Graph-like World , 1993, IJCAI.

[6]  Andrea Fabris.  Map Validation for Autonomous Driving Systems , 2020 .

[7]  Yafeng Guo,et al.  An Incremental Fusing Method for High-Definition Map Updating , 2019, 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC).

[8]  Richard Fries.  Hardware Verification and Validation , 2016 .

[9]  M Marvin Raaijmakers,et al.  Towards environment perception for highly automated driving:with a case study on roundabouts , 2017 .

[10]  Klaus C. J. Dietmayer,et al.  Robust and real-time multi-cue map verification for the road ahead , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[11]  Klaus C. J. Dietmayer,et al.  Towards autonomous self-assessment of digital maps , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[12]  Myoungho Sunwoo,et al.  Simultaneous Localization and Map Change Update for the High Definition Map-Based Autonomous Driving Car , 2018, Sensors.

[13]  Clément Zinoune,et al.  A sequential test for autonomous localisation of map errors for driving assistance systems , 2012, 2012 15th International IEEE Conference on Intelligent Transportation Systems.

[14]  Xiaolong Hu,et al.  Autonomous Driving in the iCity—HD Maps as a Key Challenge of the Automotive Industry , 2016 .

[15]  Ilja Radusch,et al.  Deriving HD maps for highly automated driving from vehicular probe data , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[16]  Nanning Zheng,et al.  High-Definition Map Combined Local Motion Planning and Obstacle Avoidance for Autonomous Driving , 2019, 2019 IEEE Intelligent Vehicles Symposium (IV).

[17]  Christoph Stiller,et al.  Deep Semantic Lane Segmentation for Mapless Driving , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[18]  Florentin Wörgötter,et al.  Automatic Traffic Light to Ego Vehicle Lane Association at Complex Intersections , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[19]  Matthias Mayr,et al.  Lanelet2: A high-definition map framework for the future of automated driving , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[20]  Björn W. Schuller,et al.  Analysing communication requirements for crowd sourced backend generation of HD Maps used in automated driving , 2018, 2018 IEEE Vehicular Networking Conference (VNC).

[21]  B. Thomas,et al.  The ActMAP - FeedMAP framework A basis for in-vehicle ADAS application improvement , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[22]  Philippe Bonnifait,et al.  Estimating the reliability of georeferenced lane markings for map-aided localization , 2019, 2019 IEEE Intelligent Vehicles Symposium (IV).

[23]  Martin Lauer,et al.  Can We Trust Our Maps? An Evaluation of Road Changes and a Dataset for Map Validation , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[24]  Clément Zinoune,et al.  Detection of missing roundabouts in maps for Driving Assistance Systems , 2012, 2012 IEEE Intelligent Vehicles Symposium.