• CN:11-2187/TH
  • ISSN:0577-6686

›› 2011, Vol. 47 ›› Issue (1): 48-54.

• 论文 • 上一篇    下一篇

基于支持矢量机回归的机器人视觉系统定位精度

尹湘云;殷国富;胡晓兵;赵雪峰   

  1. 四川大学制造科学与工程学院
  • 发布日期:2011-01-05

Positioning Accuracy of Robot Vision System Based on Support Vector Machine Regression

YIN Xiangyun;YIN Guofu;HU Xiaobing;ZHAO Xuefeng   

  1. School of Manufacturing Science and Engineering, Sichuan University
  • Published:2011-01-05

摘要: 如何提高工业机器人视觉系统在不确定性动态环境中的定位精度是机器人完成复杂任务的一个关键技术问题。针对采用单摄像机的机器人和基于位置的视觉伺服控制存在的精度问题,提出一种将基于模型控制方法和基于智能计算方法相结合的方法,以面向小样本原理的支持矢量机回归来构建控制系统误差校正模型,应用该模型对机器人末端在同一个平面上的定位误差进行校正,并且与线性插值、神经网络模型的误差校正结果进行比较分析。现场试验证明,该方法有利于提高机器人的视觉定位精度,能够满足工业机器人进行抓取和装配等任务的需要。

关键词: 定位精度, 工业机器人, 视觉伺服, 支持矢量机回归

Abstract: It is now a key technical issue to improve positioning accuracy of vision-based industrial robots to carry out complex tasks in dynamic and uncertain environment. Considering the accuracy and stability issues that pertain to position-based visual servo control for the monocular industrial robot, a method by combination of a model-based control method and intelligent-based calculation method is proposed. Based on support vector machine regression (SVR) oriented to small sample principle, an error revising model of the vision system for robots is constructed. A practical method based on SVR is designed to revise the planar positioning errors of robot manipulators, and compared with the error revising method based on linear interpolation and neural network. The experimental results demonstrate that this method can improve positioning accuracy of the vision-based robot and satisfy the demand of the location precision for industrial robots to carry through tasks, such as grabbing and assembly.

Key words: Industrial robot, Positioning accuracy, Support vector machine regression, Visual servo

中图分类号: