Robot grabbing control method and device, storage medium and robot

Abstract

The embodiment of the invention relates to a robot grabbing control method and device, a storage medium and a robot. The robot grabbing control method comprises the following steps: obtaining an image of a teaching object; determining the pose of the teaching object according to the image of the teaching object; obtaining human hand grabbing images when the teaching object is grabbed by a human hand at different teaching object poses; determining the grabbing pose of the robot according to the hand grabbing images; establishing a teaching one-to-one correspondence relationship between the teaching object poses and the grabbing pose of the robot, and storing the teaching one-to-one correspondence relationship, wherein the teaching object poses comprise teaching object poses of different teaching objects and different 6D poses of the same teaching object. According to the embodiment of the invention, the teaching process of the robot is simplified, the efficiency is improved, a proper grabbing pose can be appointed for the object, and the grabbing precision and reliability are ensured.

Description

technical field [0001] The present disclosure relates to the technical field of robots, and in particular, to a robot grasping control method, device, storage medium and robot. Background technique [0002] With the development of robot technology, robot technology is more and more used in industrial production, and robots need to adapt to the changes of products on the production line. [0003] In order to improve production efficiency, robots are used to grab the target products. At present, the robot's grasping action is mainly realized through manual methods such as repeated debugging of the teach pendant or dragging and teaching, which requires the operator to have rich operating experience for the robot, and the existing teaching pendant and drag and drop teaching are cumbersome. , Low efficiency. In addition, in the prior art, it is difficult to specify a suitable grasping pose for the grasping object in the way of automatically generating the robot's grasping pose ...

AI Technical Summary

Problems solved by technology

At present, the robot's grasping action is mainly realized through manual methods such as repeated debugging of the teach pendant or dragging and teaching, which requires the operator to have rich operating experience for the robot, and the existing teaching pendant and drag and drop teaching are cumbersome. , low efficiency

In addition, in the prior art, it is difficult to specify a suitable grasping pose for the grasping object by automatically generating the robot's grasping pose through artificial intelligence and machine vision.

Images