Mechanical arm fine adjustment control quantity interpretation method and computer readable storage medium

Abstract

The invention discloses a mechanical arm fine adjustment control quantity interpretation method and a computer readable storage medium. The method comprises the following steps: pre-storing a target scene image; acquiring a real-time scene image; extracting reference scale marks from the target scene image and the real-time scene image respectively, and correcting the real-time scene image according to the scale relation between the two images to obtain a corrected image, wherein the imaging size of the corrected image is the same as that of the target scene image; determining the to-be-moved amount of a mechanical arm in the optical axis direction according to a scale change relation between the real-time scene image and the corrected image; and extracting positioning reference points from the target scene image and the corrected image respectively, and calculating the to-be-moved amount of the mechanical arm in the direction perpendicular to the optical axis according to the position deviation between the two positioning reference points. According to the method, the accurate control quantity can be measured without requiring that a camera is of accurate or effective camera position attitude calibration parameters, and the adaptability is high.

Description

technical field [0001] The invention relates to the technical field of measurement and control, in particular to a method for interpreting fine-tuning control quantities of a mechanical arm and a computer-readable storage medium. Background technique [0002] The key step in the motion control of the manipulator is the relative position measurement of the end of the manipulator (manipulator or operating gripper) and the operating object (grabbing target, stakeout position). One type of existing method is to install a high-performance camera at the end of the manipulator. By installing a complex hand-eye system in the manipulator controller, the manipulator controller processes the imaging information of the hand-eye system in real time, and uses the image information of the cooperative target in the field of view to perform solve. Another type of typical solution is to install visual monitoring measurement or active monitoring and measurement system equipment in the working...

AI Technical Summary

Problems solved by technology

[0003] In the process of realizing the present invention, the inventor found that the disadvantage of the relative position measurement method based on the hand-eye system of the robotic arm is that it requires strong professionalism, requiring professionals to calibrate the camera parameters and the three-dimensional structure of the cooperation target in advance, and the ability to work after changes in working conditions Will fail, the adaptability of this method to automatic processing needs to be further improved, the requirements for the working environment are high, and the adaptability to external disturbances such as significant illumination changes and target changes is poor

[0004] However, the relative position measurement method based on monitoring image calculation is often used in the field with a single working environment. It requires binocular or multi-eye cameras to simultaneously image the target and the robotic arm. The working range is small and the accuracy is difficult to guarantee.

[0005] In the relative position measurement method based on active sensor monitoring, an active ranging device such as a laser range finder or an infrared active range finder is installed at the end of the manipulator, and the distance between the manipulator and the operating target is calculated by processing the detection data of the active device. This is also a self-feedback processing system. The disadvantages are high cost, high professional requirements for use and maintenance, and large equipment volume and weight.

Images