Control method and device for grabbing equipment, storage medium and electronic equipment

Abstract

The invention relates to a control method and device for grabbing equipment, a storage medium and electronic equipment, and aims to solve the problem of low grabbing accuracy of the grabbing equipment. The method comprises: determining target grabbing posture information of a gripper of grabbing equipment according to a first RGB image of a target object; after the gripper is in a posture corresponding to the target gripping posture information, acquiring a second RGB image of the target object acquired by image acquisition equipment arranged on the gripper; generating at least one piece of offset information, wherein the offset information comprises the moving direction and the moving offset of the gripper with the grabbing center point corresponding to the target grabbing posture information as the starting point; for each piece of offset information, inputting the offset information, the second RGB image and the target object mask image into a grabbing success rate prediction model;determining target offset information according to the offset information corresponding to the maximum prediction success rate, and controlling the gripper to move according to the target offset information; and after the gripper moves in place, controlling the gripper to grab the target object.

Description

technical field [0001] The present disclosure relates to the field of robots and computers, and in particular, to a control method, device, storage medium and electronic equipment for grabbing equipment. Background technique [0002] Object grasping is a widely studied problem in robotics. A common object grasping method is the geometric analysis method. The geometric analysis method assumes that the object and the object grasping point are known, and constructs a 3D object model for the known object in the database in advance, and marks the grasping position of the object respectively. For the evaluation criteria of the object grasping position, in practical application, based on the visual and geometric similarity, match the RGB-D depth image of the object to be grasped with the 3D object model stored in the database, and determine the corresponding object Grab point. However, the above-mentioned geometric analysis method does not perform well in the actual physical gras...

AI Technical Summary

Problems solved by technology

However, the above-mentioned geometric analysis method does not perform well in the actual physical grasping scene, and the problem of grasping failure often occurs

In addition, when grasping an object, the gripper is often controlled to move towards the object to be grasped by continuously giving the next grasping command. Therefore, in the process of controlling the movement of the gripper, it is necessary to obtain the The object image of the frame is used to generate the grabbing instruction, which not only has a large amount of calculation, but also the accuracy is not ideal

Images