Robot Vision Grasping Method

Abstract

The invention discloses a robot vision grasping method. The robot vision grasping method includes the steps that a product information tag is arranged on a to-be-grasped product, wherein the product information tag comprises size information of the to-be-grasped product and information of the position of the product information tag on the to-be-grasped product; the to-be-grasped product is conveyed through a conveying device; the conveying device is allowed to stop conveying of the to-be-grasped product; a picture of the to-be-grasped product in the static state is obtained through an image obtaining device, wherein the picture comprises an image of the product information tag; the image obtaining device transmits the picture to an image processing control device, and in this way, the image processing control device obtains the information of the position of the product information tag relative to the image obtaining device, the size information of the to-be-grasped product and the information of the position of the product information tag on the to-be-grasped product according to an image of the product information tag in the picture; and the image processing control device transmits corresponding indication information to a robot to control the grabbing action of the robot on the to-be-grasped product in the static state.

Description

technical field [0001] The invention relates to the field of visual recognition and automatic control, in particular to a robot visual grasping method. Background technique [0002] At present, when robots (specifically, robot arms) are used to grab products on the conveyor belt on the assembly line, camera equipment is generally used to take images of the products, and then image processing is performed on the captured images to obtain information such as product dimensions. product information. The product information is then sent to the robot's control unit, enabling the robot to control the specific operations of the robotic arm based on product information, such as product dimensions and product locations as shown in photos. [0003] However, this prior art approach to robotic vision grasping has several disadvantages. Specifically, this robotic visual grasping method in the prior art requires a large amount of calculation, and the product size and product position ne...

AI Technical Summary

Problems solved by technology

[0003] However, this robotic vision grasping method of the prior art has several disadvantages

Specifically, this robotic visual grasping method in the prior art requires a large amount of calculation, and it is necessary to calculate the product size and product position from the photo information

Secondly, due to the complex calculation process, the timeliness of the operation is poor

Moreover, the information obtained from product photos sometimes has deviations, which may cause deviations in the grasping operation of the robot arm on the product

Images