Map element extraction method of automatic mapping robot

Abstract

The invention provides a map element extraction method of an automatic mapping robot, and belongs to the technical field of navigation. The method includes steps: obtaining first map element information of a to-be-detected environment, and constructing a point cloud contour map of the to-be-detected environment, wherein the first map element information includes point cloud information of the position of the to-be-detected environment; detecting a visual mark of the to-be-detected environment at a set position, and reading second map element information included by the obtained visual mark; and marking the second map element information in the point cloud contour map, and obtaining a map including specific semantic information, wherein the second map element information comprises the specific semantic information of the map element corresponding to the position of the visual mark. According to the method, point cloud mapping and semantic marking can be automatically completed, a high-precision semantic map can be obtained, the cost is low, the implementation is easy, and the extensibility is good.

Description

technical field [0001] The invention belongs to the technical field of navigation, and relates to a map element extraction method, in particular to a map element extraction method for an automatic mapping robot. Background technique [0002] In recent years, with the gradual application of self-driving cars in some fields, the huge demand for high-precision maps used by self-driving cars and the high collection cost and cumbersome collection process of high-precision semantic maps have created a large Contradiction, it brings considerable difficulty to its large-scale practical application. At present, in the process of map collection, the local map can be constructed in the form of point cloud map established by lidar, and the automatic algorithm is used to splicing and extracting the outline of the point cloud partial map, and finally a global outline map can be generated. [0003] However, due to the segmentation and recognition of the semantic information (such as type,...

AI Technical Summary

Problems solved by technology

[0003] However, due to the segmentation and recognition of the semantic information (such as type, size, and location) of the map elements themselves by the current automatic algorithm, the accuracy and calculation speed are still difficult to reach the level of manual labeling. Therefore, in the post-processing stage of the high-precision map At present, it still needs to rely on a lot of manpower and time to carry out manual semantic annotation of map elements on the global outline map collected by the program

In this process, it will bring a lot of manpower and time costs, which will hinder the large-scale application of high-precision maps on self-driving cars.

Images