基于机器人的小件化工包裹精准分拣实验  

Precise sorting experiment of small chemicalparcels based on robot

作　　者：穆龙涛 任军辉 赵明威 王建军 周云飞 MU Longtao;REN Junhui;ZHAO Mingwei;WANG Jianjun;ZHOU Yunfei(Department of Mechanical Engineering,Shaanxi Polytechnic Institute,Xianyang 712100,Shaanxi China;Xianyang Key Laboratory of New power and Intelligent Microgrid System,Xianyang 712000,Shaanxi China;Department of Mechatronic Engineering,Xi'an Technological University,Xi'an 710032,China)

机构地区：[1]陕西工业职业技术学院机械工程学院,陕西咸阳712000 [2]咸阳市新能源及微电网系统重点实验室,陕西咸阳712000 [3]西安财经大学管理学院,陕西西安710100

出　　处：《粘接》2022年第8期115-118,132,共5页Adhesion

基　　金：陕西省自然科学基础研究计划项目(项目编号:2021JQ-896);西安财经大学2020年度科学研究扶持计划项目(项目编号:20FCZD03);陕西工业职业技术学院博士科研启动基金项目资助(项目编号:2020-05)。

摘　　要：化工行业生产潜在危险因素多,使用机器人代替人工进行危险环境作业,有效减少事故风险。针对机器人分拣作业效率低、精确度差及定位不准等问题,提出基于视觉信息感知方法,通过包裹图形识别与定位,分拣机器人精确完成分拣动作,搭建了分拣机器人验证实验平台样机,进行了机器人包裹分拣验证试验。结果表明:分拣机器人试验样机对包裹图像识别准确率平均值为96.67%,包裹分拣成功率平均值91.03%,单个包裹分拣的平均时间为1.12 s,实现了机器人对包裹的分拣。There are many potential dangerous factors in the production of the chemical industry.Using robots instead of manual operations in dangerous environments can effectively reduce the risk of accidents.Aiming at the problems of low efficiency,poor accuracy and inaccurate positioning of robot sorting operation,a method based on visual information perception is proposed.Through parcel graphic recognition and positioning,the sorting robot accurately completes the sorting action.A prototype of the sorting robot verification experimental platform is built,and the robot parcel sorting verification test is carried out.The results show that the average accuracy of parcel image recognition of the sorting robot test prototype is 96.67%,the average success rate of parcel sorting is 91.03%,and the average time of single parcel sorting is 1.12 s.the sorting of parcels by the robot is realized.

关 键 词：机器人 化工 包裹分拣 多姿态 抓取方法 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TQ205[自动化与计算机技术—控制科学与工程]