HD Map
Used for Self-Driving Cars.
Podcast episode on HD map: https://a16z.com/2017/09/16/exploding-map-evolution-cartography-deep-map/
HD map holds GPS coordinates.
HD maps can be precise at a centimetre level.
HD maps are often captured using an array of sensors, such as LiDARs, radars, digital cameras, and GPS. HD maps can also be constructed using aerial imagery.
High-definition maps for self-driving cars usually include map elements such as road shape, road marking, traffic signs, and barriers.
- https://www.geospatialworld.net/article/hd-maps-autonomous-vehicles/
- https://ieeexplore.ieee.org/abstract/document/6856487
- Lanelet2: https://www.mrt.kit.edu/z/publ/download/2018/Poggenhans2018Lanelet2.pdf
Some problems to argue against the use of HD Map
Inspiration of thought from here. HD Maps potentially impede on Privacy. This is why if you build a self-driving car that doesn’t rely on an HD map, it’s a good thing. And this is how humans drive.
ASAM openDRIVE
CARLA AD Challenge provide them in an OpenDrive format with XML Syntax.
“The data that is stored in an ASAM OpenDRIVE file describes the geometry of roads, lanes and objects, such as roadmarks on the road, as well as features along the roads, like signals”.