Yesterday, today and tomorrow of autonomous navigation maps

doi:10.11947/j.AGCS.2022.20220198

Abstract

Abstract: Taking the evolutionary background of driverless technology as the starting point, this paper reviews the concept of autonomous navigation maps, i.e., high definition maps or HD maps, along with their content components, data sources and differences from ordinary navigation maps. On this basis the author introduces the main modules of the HD mapping process, including data acquisition and update of the a priori map layer, real-time construction of the dynamic map layer, edge computing, data standardization and compression services. Four main research bottlenecks are highlighted: ① automatic modeling of complex driving environments; ② data acquisition for corner cases; ③ navigation decisions in ethical dilemmas; ④ safety performance evaluation of driverless technologies. These bottlenecks are challenging the limits of autonomous navigation capability of HD maps from different perspectives, and demand a global collaboration among government legislatures, related enterprises, research institutions, and the public. With the continuous improvement of driverless technology, the focus of safety-first research will gradually expand into a mobile experience that balances safety and trustworthiness, environmental protection and energy saving, and physical and mental pleasure. The structured digital code of HD maps will be customized to a diverse range of high legibility maps for the human eye. How to leverage the cost-effectiveness of navigation data, generate high precision maps and high legibility maps in real time, and provide optimal services for both machines and humans will become a new research hotspot.

Key words: driverless vehicles, high definition maps, edge computing, behavior prediction, corner cases, ethical dilemmas

CLC Number:

P208

MENG Liqiu. Yesterday, today and tomorrow of autonomous navigation maps[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(6): 1029-1039.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: http://xb.chinasmp.com/EN/10.11947/j.AGCS.2022.20220198

http://xb.chinasmp.com/EN/Y2022/V51/I6/1029

References

[1] LAFRANCE A. Your grandmother's driverless car[J/OL]. The Atlantic. (2016-06-29). http://www.theatlantic.com/technology/archive/2016/06/beep-beep/489029.
[2] ZHANG Meng, YAO Wei, MENG Liqiu. Enrichment of topographic road database for the purpose of routing and navigation[J]. International Journal of Digital Earth, 2014, 7(5):411-431.
[3] GRÖGER G, KOLBE T H, CZERWINSKI A. Candidate OpenGIS^{^®} CityGML Implementation Specification Version:0.3.0[S]. Open Geospatial Consortium Inc. 2006.
[4] ELLIS C. Mapping the world:Solving one of the biggest challenges for autonomous cars[J/OL]. TechRadar. pro. (2019-04-12). http://www.techradar.com/news/mapping-the-world-solving-one-of-the-biggest-challenges-for-autonomous-cars.
[5] MATTHEWS K. What are HD maps, and how will they get us closer to autonomous cars?[J/OL]. IoT Times. (2019-09-16). https://iot.eetimes.com/what-are-hd-maps-and-how-will-they-get-us-closer-to-autonomous-cars.
[6] BILLINGTON J. Toyota's self-driving spin-off trials new HD mapping technology[J/OL]. Autonomous Vehicle International. ADAS. (2019-03-01). http://www.autonomousvehicleinternational.com/news/adas/toyotas-self-dri-ving-spin-off-trials-new-hd-mapping-technology.html.
[7] TIEDEMANN Y, NAGEL P. Autonomes Fahren-Wie Entwickler den Datenbergen zu Leibe rücken[J/OL]. automotiveIT. (2021-11-11). http://www.automotiveit.eu/technology/autonomes-fahren/datenmassen-im-autonomen- auto-291.html.
[8] 司伟. 高精度地图:自动驾驶时代的基础设施[R]. 广州:广州广证恒生证券研究所有限公司, 2019. SI Wei. High definition maps:Infrastructure for the age of autonomous driving[R]. Guangzhou:Guangzhou Guang Zheng Hang Sheng Securities Research Institute Co., 2019.
[9] DAHLSTRÖM T. How accurate are HD maps for autonomous driving and ADAS simulation?[J/OL]. Atlatec, (2020-10-22). https://atlatec.de/de/blog/how-accurate-are-hd-maps-for-autonomous-driving-and-adas-simulation.
[10] 刘旷. 在即将到来的AI智能地图新时代, 新玩家还有机会吗?[J/OL]. OFweek. (2020-12-16). http://www.ofweek.com/auto/2020-12/ART-70109-8140-30474976.html. LIU Kuang. Do new players still have a chance in the coming new era of AI intelligent maps?[J/OL]. OFweek. (2020-12-16). http://www.ofweek.com/auto/2020-12/ART-70109-8140-30474976.html.
[11] ROMERO A. Tesla AI Day. Review-Part 1:The promise of full self-driving cars[J/OL]. Towards data science. (2021-09-05). https://towardsdatascience.com/tesla-ai-day-2021-review-part-1-the-promise-of-fully-self-driving-cars-8e469265509b.
[12] HARVEY S, LEE A. Introducing:The fingerprint base Map^TM for autonomous vehicle mapping and localization[J/OL]. Civil Maps. (2018-01-09). https://medium.com/@CivilMaps/introducing-the-fingerprint-base-map-for-autonomous-vehicle-mapping-and-localization-649dbd1e4810.
[13] TRINKWON W. Analysis:Will intelligent roads finally move self-driving cars into the fast lane?[J/OL]. Autocar News. (2021-02-22). https://www.autocar.co.uk/car-news/industry-news-tech%2C-development-and-manufacturing/analysis-will-intelligent-roads-finally.
[14] CAMARA F, BELLOTTO N, COSAR S, et al. Pedestrian models for autonomous driving Part Ⅱ:High-level models of human behavior[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(9):5453-5472.
[15] MCDUFF D, SONG Yale, VEMPRALA S, et al. CausalCity:Introducing a high-fidelity simulation with agency for advancing causal reasoning in machine learning[J/OL]. Microsoft Research Blog. (2021-06-29). https://www.microsoft.com/en-us/research/blog/causalcity-introducing-a-high-fidelity-simulation-with-agency-for-advancing- causal-reasoning-in-machine-learning.
[16] TAFAJ E, KASNECI G, ROSENSTEILW, et al. Bayesian online clustering of eye movement data[C]//Proceedings of the Symposium on Eye Tracking Research and Applications. Santa Barbara, California:ACM, 2012:285-288.
[17] CENSI A, SLUTSKY K, WONGPIROMSARN T, et al. Liability, ethics, and culture-aware behavior specification using rulebooks[C]//Proceedings of 2019 International Conference on Robotics and Automation (ICRA). Montreal, QC, Canada:IEEE, 2019:8536-8542.
[18] BLUMENTHAL M S, FRAADE-BLANAR L, BEST R, et al. Safe enough:Approaches to assessing acceptable safety for automated vehicles[R].[S.l.]:Rand Corporation, 2020.
[19] European Commission. Ethics of connected and automated vehicles[R].[S.l.]:Publications Office, 2020.
[20] STILGOE J. How can we know a self-driving car is safe?[J]. Ethics and Information Technology, 2021, 23(4):635-647. DOI:10.1007/s10676-021-09602-1.
[21] MIT R. Two years since the tesla GPS hack[J/OL]. GPS World. (2021-08-30). https://www.gpsworld.com/two-years-since-the-tesla-gps-hack.
[22] NORJAMÄKI N. Otaniemi, meet A!ex[J]. Aalto University Magazine, 2021:29(10):40-41.
[23] PEGASUS project office. Pegasus Method-An Overview[R]. Berlin:PEGASUS, 2019.