计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (34): 11-14.DOI: 10.3778/j.issn.1002-8331.2010.34.004

• 博士论坛 • 上一篇    下一篇

基于免疫进化的并联机器人的位姿估计

张淑平1,丁永生1,2,郝矿荣1,2   

  1. 1.东华大学 信息科学与技术学院,上海 201620
    2.数字化纺织服装技术教育部工程研究中心,上海 201620
  • 收稿日期:2010-08-20 修回日期:2010-10-25 出版日期:2010-12-01 发布日期:2010-12-01
  • 通讯作者: 张淑平

Immune evolutionary algorithm based poses estimation for parallel robot

ZHANG Shu-ping1,DING Yong-sheng1,2,HAO Kuang-rong1,2   

  1. 1.College of Information Sciences and Technology,Donghua University,Shanghai 201620,China
    2.Engineering Research Center of Digitized Textile & Fashion Technology,Ministry of Education,Shanghai 201620,China
  • Received:2010-08-20 Revised:2010-10-25 Online:2010-12-01 Published:2010-12-01
  • Contact: ZHANG Shu-ping

摘要: 提出了一种基于免疫进化算法的并联机器人位姿估计算法。建立了视觉检测坐标系和位姿参数估计模型;借鉴生物免疫系统中克隆变异和免疫记忆机理,通过免疫进化获得位姿参数的可行解。实验表明,相较于传统迭代算法,基于免疫进化算法的位姿检测算法收敛快,精确度高,对噪声不敏感,具有较好的鲁棒性。

关键词: 免疫进化算法, 并联机器人, 点相关, 位姿估计, 视觉检测

Abstract: Based on immune systems,a new immune evolutionary algorithm is presented to develop a pose estimation method for a parallel manipulator.Firstly,the coordinates are established for vision detection,and the parameter model is given.Then,profiting from the clonal variation and the immune remember mechanism of the biology immune system,the feasible solutions of the pose parameters are obtained through the immunity evolution.The experimental results indicate that the immune algorithm based pose estimation method has several merits by comparing with the traditional iterative methods.It has a high precision and converges quickly.Besides,it is insensitive to the noise and has a good robustness.

Key words: immune evolutionary algorithm, parallel manipulator, point correspondence, pose estimation, vision detection

中图分类号: