High-precision map generation method, high-precision map positioning method and high-precision map positioning device

Abstract

The invention relates to a high-precision map generation method, a high-precision map positioning method and a high-precision map positioning device, which are used for improving the positioning accuracy of a high-precision map in a special environment. The high-precision map generation method comprises the steps of acquiring target polarization information collected by a radar sensor of a measurement device, and the target polarization information being used for describing target boundary information and target attribute information; determining a radar feature layer according to the target polarization information and the positioning information of the measurement device; and generating the high-precision map according to the radar feature layer.

Description

technical field [0001] The embodiments of the present application relate to the technical field of intelligent networked vehicles, and in particular to a method for generating a high-precision map, a positioning method and a device. Background technique [0002] With more and more urban vehicles, the traffic is becoming more and more congested. In order to accommodate the increasing traffic flow, the design of urban roads is becoming more and more complicated. However, the vehicle positioning method obtained through GNSS positioning may not meet the driving requirements in some subdivided scenarios of autonomous driving. For example, GNSS positioning is used in tunnels, tunnels, elevated and other scenarios. There is a high probability that GNSS positioning signals cannot be obtained, resulting in the inability to realize driving requirements in scenarios such as automatic driving. [0003] Based on this, there is currently a method of positioning the vehicle through simult...

AI Technical Summary

Problems solved by technology

[0004] However, the above method relies too much on the camera. When the weather conditions are relatively bad, for example, when the visibility is low or objects on the road are covered or blocked by fallen leaves, effective environmental information cannot be captured by the camera to achieve positioning, and the reliability is low. At the same time, the positioning accuracy of the above method is also low.

Images