摘要
为实现机械臂在其工作范围内对任意位置的目标的抓取,提出一种基于增强现实(AR)技术机械臂物料抓取系统。系统采用多目视觉对目标定位,其中,单目视觉根据单目视觉原理建立全局空间定位模型并同时将摄取的环境上传至上位机,双目视觉基于改进的BM匹配算法获取目标的深度信息,转换得到目标的三维信息,然后将坐标信息传递给机械臂,驱动机械臂根据坐标实现对目标物的抓取。最后进行立体匹配试验和目标抓取实验。实验结果表明:基于AR技术机械臂物料抓取系统结构简单,目标识别速度快,精度高,系统的安全性和稳定性较高,具有很大的推广价值。
In order to grasp the object at any position within the working range of the manipulator,a material grasping system based on augmented reality technology is proposed.The system uses multi vision to locate the target.Monocular vision establishes the global spatial positioning model according to the monocular vision principle,and uploads the captured environment to the host computer at the same time.Binocular vision obtains the depth information of the target based on the improved BM matching algorithm,transforms the threedimensional information of the target,and then transmits the coordinate information to the manipulator,which drives the manipulator to realize the target positioning according to the coordinates grasp the target.Finally,stereo matching experiment and target grabbing experiment are carried out.The experimental results show that:Based on AR technology,the mechanical arm material grabbing system has the advantages of simple structure,fast target recognition speed,high accuracy,high security and stability,and has great promotion value.
作者
张青春
姚胜
郭振久
何孝慈
ZHANG Qingchun;YAO Sheng;GUO Zhenjiu;HE Xiaoci(Automation Faculty,Huaiyin Institute of Technology,Huai’an 223003,China)
出处
《中国测试》
CAS
北大核心
2021年第11期41-46,共6页
China Measurement & Test
关键词
机械臂
机器视觉
BM匹配
三维重建
manipulator
machine vision
BM matching
3D reconstruction