Self-driving cars are no longer a futuristic idea. Major auto manufacturers have already released, or are soon to release, self-driving features that give the car some ability to drive itself. In order to operate safely, autonomous vehicles will require purpose-built map-based datasets, which contain significantly more detailed information and true-ground-absolute accuracy than those found in current conventional resources.
Sanborn’s Advanced Technology group has developed proprietary HAD Mapping technology that leverages Aerial Imagery, Aerial LiDAR data, and Mobile (driven) LiDAR data to create standardized, high-precision 3D base-maps focusing specifically on self-driving vehicle models and markets.
Sanborn HD Maps For Autonomous Driving Feature:
- Accuracy in the 7-10cm absolute ranges.
- Highly detailed inventories of all stationary physical assets related to roadways such as road lanes, road edges, shoulders, dividers, traffic signals, signage, paint markings, poles, and all other critical data needed for the safe navigation of roadways and intersections by autonomous vehicles.
- Electronic Horizon Predictive Awareness – autonomous vehicles will know what lies ahead.
- OpenDrive and NDS format compatibility.
- ADASIS v2 standardization.
- Proprietary Geo-Database schematics that have been reviewed by top-level industry consultants.
- Integration compatibility with all forms of Municipal Data, Vehicle Supplied Data, and Crowd-Sourced datasets.
- Conflation functionality designed to improve the absolute accuracy of 3rd party Road Data (probe or alternative source) to high-precision standards.
- Online web-based analytics – designed for auto teams to review / discuss vector and point data super-imposed digitally on top of high-resolution imagery.
- Lightweight data size – data is optimized and compressed for onboard CPU systems.
Sanborn HD Maps – Complex Urban Datasets
Sanborn collected aerial and street-level data for the Silicon Valley area (Santa Clara) in Spring 2016 and constructed sizable target areas in Sunnyvale (Heritage District), Palo Alto, and surrounding locations. Sanborn teams are refreshing and expanding all of the 2016 HD Maps with new 2017 data – showcasing Sanborn advanced change detection algorithms and road network feature update programs. Sanborn HD Maps for Autonomous Driving data is currently available for California and Michigan.
HD Map – Precision 3D Road Network Data Features:
- All road network features are available as precision 3D global data files (GeoJSON, ShapeFiles, and CSV in WGS-84 projection).
- All road network features are attributed and classified for the most sophisticated autonomous driving programs.
- Datasets are available for all environments and levels of autonomous drive testing complexity – Freeway, Complex Urban, Complex Parking, etc.
- Complex Urban HD Map datasets deliver high-precision road feature intelligence:
A. Painted Lines – All painted lines assembled as precision 3D map features, polygons, and lines.
B. Signs – All signs represented as locational precision XYZ features designed to guide the most advanced target recognition for high precision localization.
C. 3D Building Models – All buildings constructed and attributed with height points for advanced 3D City Model visualization.
D. Signals and Stop Lines – Traffic signals and stop lines collected in absolute 3D XYZ space delivering precise locations for intersection control protocols.
E. Parking Spaces – Each parking space attributed with a unique ID, geometric shape, and centroid location.