摘要
为提升物流机器人的灵活性和智能化水平,将全向移动平台、物料抓取机器人、双目视觉识别等技术进行集成应用研究。分析了机器人的结构布局和运动学模型,完成了机械臂的机构原理设计,结合计算机应用视觉识别算法,选择具体的检测方法完成识别对象的角点、边缘及轮廓检测,实现对象的图像处理。通过双目相机成像模型实现坐标系之间的转换,达到定位目标物品的目的。最后,完成了物理样机的开发和实地操作的实验验证。实验结果表明,该系统可以有效地完成物品识别、抓取和搬运工作。
In order to improve the flexibility and intelligence level of the logistics robot,the integrated application of omnidirectional mobile platform,material grabbing robot and binocular vision recognition technology is developed in this paper.The structure and mathematical models of the robot are analyzed,and the mechanism design of the manipulator is completed.By combining the computer vision recognition algorithm,a specific detection method is selected to complete the detection of the corner,edge and contour of the object and the image processing of the object is realized.Through the binocular camera imaging model,the transformation between coordinate systems can be realized to achieve the goal of locating objects.Finally,the design of the physical prototype is completed,and the practical operation is verified by experiments.The manufacturing and experimental verification of the physical prototype are carried out.The experimental results show that the robot system can effectively identify,grab and transport items.
作者
高振清
李明刚
杜艳平
武泽鹏
卢杰辉
张媛
Gao Zhenqing;Li Minggang;Du Yanping;Wu Zepeng;Lu Jiehui;Zhang Yuan(School of Mechanical and Electrical Engineering,Beijing Institute of Graphic Communication,Beijing 102600,China;Beijing 6-Robot Technology Co.,Ltd.,Beijing 100088,China)
出处
《机械科学与技术》
CSCD
北大核心
2019年第5期779-782,共4页
Mechanical Science and Technology for Aerospace Engineering
基金
轨道交通控制与安全国家重点实验室开放课题基金项目(RCS2016K005)资助
关键词
全向移动
双目视觉
抓取
搬运
识别
物流
robot
computer vision
mathematical models
identification
design
experiments