doi:10.16186/j.cnki.1673-9787.2020100050

Received:2020/10/21

Revised:2021/02/08

Published:2022/01/10

Design of positioning system of industrial robot with monocular vision based on embedded system

WANG Shaofeng 1, XIA Guangyuan 1, JI Chunsheng 2, WANG Hailing 3

1.School of Mechanical Engineering， Inner Mongolia University of Science and Technology， Baotou  014010 ， Inner Mongolia ， China；2.Baotou Special Equipment Inspection Institution， Baotou  014030 ， Inner Mongolia， China；3.Inner Mongolia North Heavy Industries Group Corp. Ltd. ， Baotou  014033，InnerMongolia，China

Abstract:  In order to solve the problems of the traditional industrial robot control method，the positioning of industrial robots guided by machine vision was studied，and a low-cost system solution based on the KUKA robot arm and the embedded ZYNQ development board as the hardware platform was proposed． Firstly，a mathematical model was established for the visual positioning and grasping of industrial robots． Secondly，the image processing technology based on machine vision was studied，and the pre-processed workpiece contour was recognized and positioned with contour characteristic parameters as identification conditions． Finally，the real pose of the workpiece was sent to the industrial robot control system to guide grasping after coordinate conversion． Experimental results showed that the system could realize effective and accurate positioning of target workpieces．

Key words:embedded system;machine vision;monocular vision;industrial robot;image processing

 基于嵌入式的单目视觉工业机器人定位系统设计_王少锋.pdf