High-precision map automatic generation method based on high-precision positioning and lane line recognition

Abstract

The invention discloses a method for automatically generating a high-precision map based on high-precision positioning and lane line recognition. into the map frame database; match the newly acquired lane line data with all the established map frames, if the matching fails, a new map frame will be established; if the matching is successful, the information will be updated for the established map frame; Inter-frame smoothing is performed on all existing frames in the established map frame to obtain a smoothed cubic curve; a high-precision map is generated by splicing the cubic curves. The present invention generates a high-precision map that is accurate to the lane line based on high-precision positioning and can automatically stitch the lane line, reduces the complexity of generating a high-precision map, and avoids a large amount of manpower consumption and the need for traditional high-precision map production. The problem of high error rate.

Description

technical field [0001] The invention relates to the field of unmanned driving technology, in particular to a method for automatically generating a high-precision map based on high-precision positioning and lane line recognition. Background technique [0002] As a scarce resource and rigid demand in the field of unmanned driving, high-precision maps play a central role in the entire field. They can help unmanned vehicles perceive complex information on the road in advance, such as slope, curvature, heading, etc., combined with intelligent path planning, make unmanned vehicles Making correct decisions is an indispensable source of data for driverless vehicles. Unmanned driving needs to compare the information collected by the sensor with the stored high-precision map to judge the position and direction, so as to ensure the safe driving of the unmanned vehicle to the destination. Therefore, the accuracy of high-precision map data collection is very important for unmanned drivin...

AI Technical Summary

Problems solved by technology

Unmanned driving needs to compare the information collected by the sensor with the stored high-precision map to judge the position and direction, so as to ensure the safe driving of the unmanned vehicle to the destination. Therefore, the accuracy of high-precision map data collection is very important for unmanned driving. Crucial; the production of traditional high-precision maps requires a lot of manpower to label, which is not only time-consuming and labor-intensive, but also has a high error rate due to errors caused by manual labeling, which is not conducive to the development of unmanned driving. Nowadays, the production of high-precision maps , due to high precision requirements, complex calculation process, and relatively time-consuming production process, it is necessary to provide a high-precision map that can automatically splice lanes based on high-precision positioning and lane line recognition, and takes a short time.

Images