A control method of a manipulator grasping control system based on binocular stereo vision

Abstract

The invention discloses a control method of a manipulator grabbing control system based on binocular stereoscopic vision. The control method comprises the following steps: camera parameters are calibrated, and a teaching manipulator is used for realizing conversion of a camera coordinate system and a manipulator coordinate system; line laser performs an arc surface scanning cloud motion, and a camera acquires images; laser lines of the images shot by the camera are respectively extracted; the positions of the laser lines are precisely determined by using a sub pixel algorithm; the homonymy point matching is performed for the laser lines extracted in the images; three-dimensional space coordinates of all points on the laser lines are calculated through a triangular measuring principle to finish scanning of workpieces in a scene so as to obtain point cloud data in the viewing field of the camera; a workpiece point cloud template is built, a manipulator grabbing point position is selected, and the obtained point cloud data is matched with the workpiece point cloud template to calculate a conversion relation of the two; the manipulator grabbing point position in the point cloud template is converted to a present coordinate, is converted to a coordinate under the manipulator coordinate system, and is transferred to the manipulator; and the manipulator finishes actuation actions.

Description

technical field [0001] The invention relates to the field of manipulator grasping control, in particular to a manipulator grasping control based on binocular stereo vision that can obtain 3D point cloud data of workpieces in a material box in real time, and guide manipulators to grasp and place workpieces through template matching system control method. Background technique [0002] At present, industrial automation assembly has received more and more attention, and industrial assembly by vision-guided manipulator is an important way to realize industrial automation. In the process of manipulator performing tasks, it is a very critical issue to control the manipulator to locate to the target position. CN103963058A method and method for grasping control of a robotic arm based on multi-directional vision positioning, CN104331894A a method for unstacking a robot based on binocular stereo vision, and CN104677330A a small binocular stereo vision ranging system all disclose a vis...

AI Technical Summary

Problems solved by technology

However, these methods have the defects of poor recognition rate for different types of products, and the positioning accuracy is difficult to meet the requirements of grasping and placement.

Images