High-definition map

A high-definition map (HD map) is a highly accurate map used primarily in the field of autonomous driving,^[1][2] containing details not normally present on traditional maps.^[3][4] HD maps are often captured using an array of sensors, such as LiDARs, radars, digital cameras, and GPS,^[3][5][6] and they can also be constructed using aerial imagery.^[7][8] Such maps can be precise at a centimetre level.^[3][9]

A Zoox autonomous prototype vehicle, outfitted with sensors for sensing and high-definition mapping.

High-definition maps for self-driving cars usually include map elements such as road shape, road marking, traffic signs, and barriers.^[4][10] 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 (1.2 in) 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%.^[11]