Three-dimensional map generation method and apparatus, vehicle navigation device and driverless vehicle

Abstract

Embodiments of the present invention disclose a three-dimensional map generation method and apparatus, a vehicle navigation device and a driverless vehicle. According to the embodiments of the presentinvention, after road information and relative position information of a vehicle are collected, wherein the relative position information comprises information about a position of an environment surrounding the vehicle relative to the vehicle, coordinate information of a map element corresponding to the road information is labeled in the relative position information, a relative level of the mapelement is labeled according to the coordinate information, to obtain two-dimensional map data, then a three-dimensional model of a road in which the vehicle is located is constructed based on the two-dimensional map data by using the road information and the relative position information, and level matching is performed on the map element in the three-dimensional model according to the coordinateinformation and the relative level of the map element, to generate a three-dimensional map. Quality of the three-dimensional map can be significantly improved.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to a method and device for generating a three-dimensional map, a vehicle navigation device and an unmanned vehicle. Background technique [0002] In recent years, with the development of autonomous driving technology, the related vehicle navigation technology has also made great progress. The existing vehicle navigation technology mainly uses high-precision three-dimensional maps to obtain accurate vehicle location information and navigation information. The precision 3D map is still generated manually or automatically. [0003] During the research and practice of the prior art, the inventors of the present invention found that manual labeling of 3D maps is inefficient, poor in accuracy, and manual labeling in a 3D environment is difficult, while using algorithms to automatically label 3D maps has errors The higher the rate, the less stable the accuracy of the 3D map, and th...

AI Technical Summary

Problems solved by technology

[0003] During the research and practice of the prior art, the inventors of the present invention found that manual labeling of 3D maps is inefficient, poor in accuracy, and manual labeling in a 3D environment is difficult, while using algorithms to automatically label 3D maps has errors The higher the rate, the less stable the accuracy of the 3D map, and therefore the lower quality of the generated 3D map

Images