Multi-eye vision guidance driving device for automatic guided vehicle and its collaborative calibration method

Abstract

The present invention provides a multi-eye visual guidance driving device of an automatic guided vehicle and a cooperative calibration method thereof. The body of the automatic guided vehicle is fixedly connected with several guiding driving devices, and each guiding driving device includes Shock unit, drive unit and vision unit. Each vision unit has a camera, and the cameras on multiple guide drives form the multi-eye vision system of the automatic guided vehicle. The present invention utilizes the structural feature that a single guide drive device can rotate around a hollow short axis, and jointly establishes the coordinate system of the scene and the motion control coordinate system of each guide drive device and its relationship with the vehicle body through static calibration and dynamic calibration methods. The pose relationship among them effectively eliminates the distortion, scale distortion, tilt distortion of visual imaging and the installation pose error of multiple cameras. This method can be used for precise multi-eye vision measurement of automatic guided vehicles based on planar vector graphics, without the use of precision measuring instruments, and has the characteristics of good operability and high flexibility.

Description

technical field [0001] The invention relates to the field of computer vision detection, in particular to a multi-eye vision guidance drive device for an automatic guided vehicle and a collaborative calibration method thereof. Background technique [0002] Automated guided vehicle (AGV) is a wheeled mobile robot widely used in factory automation production lines, warehouse logistics, material transfer in airports and ports. Its guidance method is one of the core technologies for automatic guided vehicles to realize automatic transportation, which not only determines the flexibility of the automatic transportation system composed of it, but also affects the reliability of system operation and configuration costs. The multi-eye vision guidance method is to form the multi-eye vision system of the automatic guided vehicle through the cameras installed on each guidance drive device, and use the system to collect the images of the guidance path laid on the ground, and use the compu...

AI Technical Summary

Problems solved by technology

Although the traditional calibration method can obtain the external parameters of the camera, the parameters are only the pose relationship between the target coordinate system and the camera coordinate system

In the visual guidance application of automatic guided vehicles, it is also necessary to obtain the pose relationship between the camera coordinate system and the vehicle motion control coordinate system. It is difficult to measure the target relative to the The vehicle motion control coordinate system is precisely placed

Images