Monocular vision AGV accurate positioning method and system based on multi-window real-time range finding

Abstract

The invention discloses a monocular vision AGV (Automated Guided Vehicle) accurate positioning method and system based on multi-window real-time range finding. The method comprises according to a camera slanting installation mode, calibrating and measuring camera parameters and establishing a visual system real-time measuring model; setting a circular color lump on the ground to be used as the reference substance for parking positioning, identifying the circular color lump through the efficient algorithm of the visual system, and accurately extracting central position information; and in a view filed, setting a plurality of windows to process images a far-end window is used for an AGV to predetermine ground information so as to gradually decelerate; an intermediate window is used as a coarse positioning window, and used for adjusting poses; and a near-end window is used for accurate range finding and parking. The method allows an AGV to sense depth information, and has the advantages of high characteristic recognition rate, excellent arithmetic instantaneity, low cost and great extendibility. The horizontal distance deviation of AGV parking is stabilized at +-1 mm, the angle deviation is stabilized at +-1 DEG, and the parking error is stabilized at +- 2mm.

Description

technical field [0001] The invention relates to a precise positioning technology of an industrial mobile robot based on visual sensing, in particular to a precise positioning method and system of a monocular vision-guided AGV based on multi-window real-time ranging, which belongs to the field of intelligent industrial robots. Background technique [0002] In the automated logistics equipment, the automatic guided vehicle (AGV) is an ideal tool for material delivery and has been used in various industries of social production. During the operation of AGV, the accuracy of its walking positioning is not high, but it is required to achieve high positioning and parking accuracy at the station point. The positioning parking of AGV refers to the function that its guidance system can stop at the designated station after obtaining the information of the station point. Whether the position of positioning parking is accurate or not will directly affect the subsequent work tasks. At pr...

AI Technical Summary

Problems solved by technology

The Chinese invention patent with the publication number CN103390259A adopts a method of vertically installing the camera to detect the ground path. The vertically installed camera has relatively small image distortion and high detection accuracy, but its field of view is small, and it is impossible to obtain the road condition information in front of the AGV in time.

The Chinese invention patent with the publication number CN103646249A adopts the oblique installation method of the camera. After processing the collected images, the midpoint information of the forward path can be obtained, and the accurate measurement of the road surface information cannot be realized.

[0004] The traditional monocular vision-guided AGV does not have the real-time ranging function, lacks visual information feedback, and does not have the ability to park closed-loop control

In addition, the method of using the cross mark as the station point information only sends a parking signal to the motion controller immediately after detecting the station point. The actual parking error is relatively large, and the positioning accuracy of repeated parking is low, and the precise positioning and parking of the AGV cannot be realized.

The visual positioning method proposed by the Chinese invention patent with the publication number CN104181920A can realize the positioning of the AGV at the station point, but it is easily affected by other factors when positioning and parking, and its parking positioning accuracy is not ideal

In terms of path deviation measurement, the traditional method fits the collected path points according to the preset path model. Typical path models include straight line model, circular arc model, and non-circular arc model. And the accuracy is limited compared to the results calculated by the linear model

Images