基于改进的YOLO V3算法在装配任务中定位抓取
DOI:
作者:
作者单位:

中国石油大学(华东)机电工程学院

作者简介:

通讯作者:

中图分类号:

TP311

基金项目:

山东省重大科技创新项目(2017CXGC0902);青岛市应用基础研究项目(青年专项)(18-2-2-13-jch);中央高校基础研究经费(18CX02088A)


Positioning and Grasping in Assembly Tasks Based on Improved YOLO V3 Algorithm
Author:
Affiliation:

School of Mechanical and Electrical Engineering, China University of Petroleum (East China)

Fund Project:

Major scientific and technological innovation projects in Shandong Province(2017CXGC0902);Qingdao Applied Basic Research Project (Youth Special Project)(18-2-2-13-jch);The Fundamental Research Funds for the Central Universities(18CX02088A)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 文章评论
    摘要:

    针对视觉引导定位的机械臂抓取装配任务中对工业零件的定位差、抓取效率低等问题,提出一种基于改进的YOLO V3智能抓取系统方案,实现工业零件从目标检测到自动化抓取的智能化。首先,为提高对小目标和拥挤目标的检测性能,提出了改进的YOLO V3目标检测网络;其次,对工业零件进行数据采集与训练,实现对零件的目标识别与定位;最后,通过相机标定和手眼标定实现由图像坐标系到世界坐标系的转变,获得被抓物体的世界坐标,对机械臂进行抓取规划,完成目标物体的抓取。实验采用Kinect V2像机与UR3六轴协作机械臂组成抓取实验平台,分别进行目标零件的定位和抓取实验。实验结果表明,改进的YOLO V3增加了第4层的特征尺度目标检测,提高了对小目标和拥挤目标的检测性能,抓取系统对零件进行精准的目标定位,并成功进行了抓取。

    Abstract:

    Aiming at the problems of poor positioning and low grasping efficiency of industrial parts in the manipulator grasping assembly task of visual guidance positioning, an improved YOLO V3 intelligent grasping system solution is proposed to realize the intelligentization of industrial parts from object detection to automatic grasping. First, in order to improve the detection performance of small targets and crowded targets, an improved YOLO V3 target detection network is proposed. Secondly, data collection and training are carried out on industrial parts to realize the target recognition and positioning of the parts. Finally, through camera calibration and hand-eye calibration, the transformation from the image coordinate system to the world coordinate system is realized, the world coordinates of the grasped object are obtained, the grasping plan of the manipulator is carried out, and the grasping of the target object is completed. In the experiment, the Kinect V2 camera and the UR3 six-axis collaborative manipulator were used to form a grasping experiment platform, and the positioning and grasping experiments of the target parts were carried out respectively. The experimental results show that the improved YOLO V3 adds the fourth layer of feature-scale target detection, which improves the detection performance of small targets and crowded targets. The grasping system accurately locates the parts and successfully grasps them.

    参考文献
    相似文献
    引证文献
引用本文

李世庆,王新庆,文岩,等. 基于改进的YOLO V3算法在装配任务中定位抓取[J]. 科学技术与工程, , ():

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-08-23
  • 最后修改日期:2021-11-21
  • 录用日期:2021-12-26
  • 在线发布日期:
  • 出版日期:
×
关于近期《科学技术与工程》编辑部居家办公的说明
亟待确认的版面费信息