Article classification control system and method based on industrial robot

Abstract

The invention discloses an object classification control system and method based on an industrial robot, the control system comprises a manipulator device, a mechanical arm and a template database, the output end of the mechanical arm is provided with the manipulator device, and the template database is provided with a plurality of full-angle templates of a target object; the manipulator device is provided with a plurality of shooting modules, sending modules and object recognition modules; the shooting module is used for shooting and acquiring an image of a to-be-recognized object; the sending module is used for sending the image of the object to be recognized to the object recognition module; the object recognition module is used for extracting feature information of the to-be-recognized object image and matching the feature information with each template image of the template database to obtain a recognition result; the mechanical arm is provided with a control module, and the control module is used for generating a track instruction for controlling the mechanical arm to move and an instruction for controlling the manipulator device to grab and release the target object according to the recognition result. The problems that the manual object classification efficiency is low, and the precision of object recognition through a single recognition module is not high are solved.

Description

technical field [0001] The invention relates to the application field of mechanical arms, in particular to an object classification control system and method based on an industrial robot. Background technique [0002] With the continuous progress of social civilization, people need to manually sort a large number of objects into their respective categories when classifying objects. However, in the process of object sorting, some large objects are cumbersome and difficult for people to lift. Sorting; some small objects are relatively small, such as screws, pens, etc., people need to spend a certain amount of work to select these small objects for identification and classification, which greatly reduces the efficiency of object classification; and when people use machines When classifying objects, most of them use a single recognition module for recognition, which sometimes causes the recognition accuracy of objects to be low. SUMMARY OF THE INVENTION [0003] In view of th...

AI Technical Summary

Problems solved by technology

[0003] In view of the above defects, the present invention proposes an object classification control system and method based on industrial robots, the purpose of which is to solve the problems of low efficiency of manually classifying objects and low accuracy of identifying objects through a single identification module

Images