High-definition map

A high-definition map (HD map) is a highly accurate map used in autonomous driving,[1] containing details not normally present on traditional maps.[2][3] Such maps can be precise at a centimetre level.[2][4]

HD maps are often captured using an array of sensors, such as LiDARs, radars, digital cameras, and GPS.[2][5][6] HD maps can also be constructed using aerial imagery.[7][8]

High-definition maps for self-driving cars usually include map elements such as road shape, road marking, traffic signs, and barriers.[3][9] Maintaining high accuracy is one of the biggest challenges in building HD maps of real-world roads. With regard to accuracy, there are two main focus points that determine the quality of an HD map:

  • Global accuracy (positioning of a feature on the surface of the Earth)
  • Local accuracy (positioning of a feature in relation to road elements around it).

In areas with good GPS reception it is possible to achieve a global accuracy of less than 3 cm deviation using satellite signals and correction data from base stations.

In GPS-denied areas, however, inaccuracy rises with distance traveled through the area, being largest in its middle. This means that the maximum GPS error can be expressed as a percentage of the distance traveled through a GPS-denied area: this value is less than 0.5%.[10]

ReferencesEdit

  1. ^ Liu, Rong; Wang, Jinling; Zhang, Bingqi (27 August 2019). "High Definition Map for Automated Driving: Overview and Analysis". Journal of Navigation. 73 (2): 324–341. doi:10.1017/S0373463319000638. ISSN 0373-4633. S2CID 202906063.
  2. ^ a b c Vardhan, Harsha (2017-09-22). "HD Maps: New age maps powering autonomous vehicles". Geospatial World. Retrieved 2021-01-20.{{cite web}}: CS1 maint: url-status (link)
  3. ^ a b Matthews, Kayla (September 16, 2019). "What are HD maps, and how will they get us closer to autonomous cars?". EETimes.{{cite news}}: CS1 maint: url-status (link)
  4. ^ Jiao, J. (22 June 2018). "Machine Learning Assisted High-Definition Map Creation". 2018 IEEE 42nd Annual Computer Software and Applications Conference (COMPSAC). 01: 367–373. doi:10.1109/COMPSAC.2018.00058. ISBN 978-1-5386-2666-5. S2CID 52058583.
  5. ^ "HD maps—the hidden sensors that help autonomous vehicles see round corners". Automotive World. 14 March 2019. Retrieved 2021-01-20.{{cite web}}: CS1 maint: url-status (link)
  6. ^ Mueck, Markus; Karls, Ingolf (9 January 2018). Networking vehicles to everything : evolving automotive solutions. Boston. ISBN 978-1-5015-0724-3. OCLC 1021887635.
  7. ^ Javanmardi, Mahdi; Javanmardi, Ehsan; Gu, Yanlei; Kamijo, Shunsuke (2017-09-21). "Towards High-Definition 3D Urban Mapping: Road Feature-Based Registration of Mobile Mapping Systems and Aerial Imagery". Remote Sensing. 9 (10): 975. Bibcode:2017RemS....9..975J. doi:10.3390/rs9100975. ISSN 2072-4292.
  8. ^ Zang, Andi; Xu, Runsheng; Li, Zichen; Doria, David (2017-11-07). "Lane boundary extraction from satellite imagery". Proceedings of the 1st ACM SIGSPATIAL Workshop on High-Precision Maps and Intelligent Applications for Autonomous Vehicles. AutonomousGIS '17. Redondo Beach California: ACM: 1–8. arXiv:2002.02362. doi:10.1145/3149092.3149093. ISBN 978-1-4503-5497-4. S2CID 11512991.
  9. ^ Zang, Andi; Chen, Xin; Trajcevski, Goce (2018-06-05). "High definition maps in urban context". SIGSPATIAL Special. 10 (1): 15–20. doi:10.1145/3231541.3231546. ISSN 1946-7729. S2CID 47019015.
  10. ^ "How Accurate Are HD Maps for Autonomous Driving and ADAS Simulation?". Atlatec. 2020-10-22. Retrieved 2021-05-20.