| 引用本文: | 辛 菁,刘 丁,徐庆坤.基于LS–SVR的机器人空间4DOF无标定视觉定位[J].控制理论与应用,2010,27(1):77~85.[点击复制] |
| XIN Jing,LIU Ding,XU Qing-kun.LS–SVR-based uncalibrated 4DOF visual positioning of robot[J].Control Theory and Technology,2010,27(1):77~85.[点击复制] |
|
| 基于LS–SVR的机器人空间4DOF无标定视觉定位 |
| LS–SVR-based uncalibrated 4DOF visual positioning of robot |
| 摘要点击 2005 全文点击 1434 投稿时间：2007-09-25 修订日期：2009-01-14 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/j.issn.1000-8152.2010.1.011 |
| 2010,27(1):77-85 |
| 中文关键词 无标定 视觉定位 最小二乘支持向量回归 免疫控制 |
| 英文关键词 uncalibrated visual positioning least squares support vector regression immune control |
| 基金项目 国家自然科学基金资助项目(60675048); 陕西省自然科学基金资助项目(2009JQ8011). |
|
| 中文摘要 |
| 研究了基于智能算法的机器人无标定视觉伺服问题, 提出了一种新的基于最小二乘支持向量回归的机器人无标定视觉免疫控制方法. 利用最小二乘支持向量回归学习机器人位姿变化和观测到的图像特征变化之间的复杂非线性关系, 其中最小二乘支持向量回归的参数由自适应免疫算法加5折交叉检验优化确定, 在此基础上利用免疫控制原理设计了视觉控制器. 六自由度工业机器人空间4DOF 视觉定位实验结果表明了该方法的有效性. |
| 英文摘要 |
| The robot uncalibrated visual servoing based on an intelligent algorithm is studied; and a new robot uncalibrated visual servoing method based on the least squares support vector regression(LS–SVR) is proposed. LS–SVR is used to learn the complex nonlinear relationship between the changes of robot pose and the variations of the image features observed. The parameters of LS–SVR are determined by the adaptive immune algorithm(AIA) plus a 5-fold cross validation； and the visual controller is designed using the principle of immune feedback. 4DOF visual positioning experiments have been carried out in a 6DOF industrial robot. Experimental results testify the feasibility and validity of this method. |