AGV composite mapping and navigation positioning method and system based on SLAM

Abstract

The invention belongs to the field of navigation positioning, and provides an AGV composite mapping and navigation positioning method and system based on SLAM. In order to solve the problems that whenfine positioning and coarse positioning are switched, positioning data jump occurs in two sets of maps and positioning switching, and the customer impression and experience effect are affected, the AGV composite mapping method based on SLAM comprises the steps: receiving the point cloud data of the surrounding environment of an AGV, loading a timestamp, and then caching the point cloud data cached to an environment data pool; calling the point cloud data with the same timestamp from the environment data pool, and extracting environment feature points corresponding to the point cloud data withthe same timestamp; matching the point cloud data with the same timestamp with the surrounding environment of the AGV, constructing a point cloud map, converting the coordinates of the correspondingenvironment feature points to the coordinate system of the point cloud map, constructing a feature point map, and uniformly optimizing the point cloud map and the feature point map to realize synchronization of the point cloud map and the feature point map. The AGV positioning precision can be improved.

Description

technical field [0001] The invention belongs to the technical field of AGV mapping, navigation and positioning, and in particular relates to a SLAM-based AGV composite mapping, navigation and positioning method and system. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] With the rapid development of automation and intelligent equipment, various unmanned vehicles (including AGV and unmanned vehicles, but not limited to AGV and unmanned vehicles) can be used to realize the delivery and handling of unmanned goods, and all All unmanned transportation vehicles have their own positioning and navigation methods, and laser is one of the existing mainstream navigation methods. [0004] The inventors found that there are certain deficiencies in the traditional positioning and navigation methods, as follows: 1) The navigation method of single point ...

AI Technical Summary

Problems solved by technology

[0004] The inventors found that there are certain deficiencies in the traditional positioning and navigation methods, as follows: 1) The navigation method of single point cloud matching has low accuracy; the initial positioning of single point cloud matching will cause initial positioning errors when the map has a similar map shape 2) The navigation method of individual feature points needs to manually add a large number of feature points; the navigation method of individual feature points will have a high probability of positioning errors near the positions of similar feature points on the map; 3) The existing methods use point cloud matching to achieve coarse positioning of unimportant positions, use feature points to achieve key positions, or use point cloud positions for fine positioning. At present, the two sets of map data constructed by these two positioning methods are not synchronized in real time, resulting in fine positioning. When switching with coarse positioning, the positioning data will jump between the two sets of maps and positioning switching, which will affect the customer's perception and experience

Images