基于双目视觉引导的纸箱切割系统研究  

Research on carton cutting system based on binocular vision guidance

作　　者：刘乐 邹光明 侯宇[1,2] 刘源泂 皇甫小峰[1] LIU Le;ZOU Guangming;HOU Yu;LIU Yuanjiong;HUANGFU Xiaofeng(Key Laboratory of Mechanical Transmission and Manufacturing Engineering of Hubei Province,Wuhan University of Science and Technology,Wuhan 430081,China;Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education,Wuhan University of Science and Technology,Wuhan 430081,China)

机构地区：[1]武汉科技大学机械传动与制造工程湖北省重点实验室,武汉430081 [2]武汉科技大学冶金装备及其控制教育部重点实验室,武汉430081

出　　处：《智能计算机与应用》2023年第12期62-67,74,共7页Intelligent Computer and Applications

基　　金：湖北省技术创新专项重大项目(2018AAA027)。

摘　　要：针对传统模式机器人在仓储出库作业时缺乏智能性的问题,本文研究一种基于双目视觉引导机械臂切割系统,搭建了双目立体视觉系统并进行双目标定,通过机械臂手眼标定获得纸箱坐标系,相当于机械臂基坐标系的坐标变换,提出一种基于标准尺寸纸箱作为模板的灰度匹配方法,获得纸箱规格信息进而引导机械臂完成切割。实验结果表明,3类纸箱定位误差绝对值分别在1.3 mm、1.5 mm和2.2 mm以内,满足工业生产要求,具有较好通用性。Aiming at the lack of intelligence of the traditional mode robot in warehouse operation,this paper researches a binocular vision guidance robotic arm cutting system based on binocular vision,builds a binocular stereoscopic vision system,and performs binocular calibration,obtains the carton coordinate system equivalent to the coordinate transformation of the base coordinate system of the robotic arm through the robotic arm hand-eye calibration,and puts forward a grayscale matching method based on the standard-size carton as a template to obtain the carton specification information And then guide the robotic arm to complete the cutting.The experimental results show that the absolute values of the positioning errors of three types of cartons are within 1.3 mm,1.5 mm,and 2.2mm respectively.The vision-guided robotic arm-cutting system meets the requirements of industrial production and has good versatility.

关 键 词：视觉引导 手眼标定 灰度匹配 切割系统 

分 类 号：TP241[自动化与计算机技术—检测技术与自动化装置]