期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
A Target Grabbing Strategy for Telerobot Based on Improved Stiffness Display Device 被引量:3
1
作者 Pengwen Xiong Xiaodong Zhu +3 位作者 Aiguo Song Lingyan Hu Xiaoping P.Liu Lihang Feng 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2017年第4期661-667,共7页
Most target grabbing problems have been dealt with by computer vision system, however, computer vision method is not always enough when it comes to the precision contact grabbing problems during the teleoperation proc... Most target grabbing problems have been dealt with by computer vision system, however, computer vision method is not always enough when it comes to the precision contact grabbing problems during the teleoperation process, and need to be combined with the stiffness display to provide more effective information to the operator on the remote side. Therefore, in this paper a more portable stiffness display device with a small volume and extended function is developed based on our previous work. A new static load calibration of the improved stiffness display device is performed to detect its accuracy, and the relationship between the stiffness and the position is given. An effective target grabbing strategy is presented to help operator on the remote side to judge and control and the target is classified by multi-class SVM(supporter vector machine). The teleoperation system is established to test and verify the feasibility. A special experiment is designed and the results demonstrate that the improved stiffness display device could greatly help operator on the remote side control the telerobot to grab target and the target grabbing strategy is effective. 展开更多
关键词 multi-class svm(supporter vector machine) TELEOPERATION target grabbing stiffness display
下载PDF
基于支持向量数据描述算法的SVM多分类新方法 被引量:4
2
作者 张贝贝 何中市 《计算机应用研究》 CSCD 北大核心 2007年第11期46-48,共3页
提出一种基于支持向量数据描述算法(SVDD)的多分类方法(S-MSVM)。受SVDD的启发,该方法对每类样本建立一个超球来界定,但训练好的超球在所有情况下都是相交的。选择相交区域的样本单独建立超球,重复该步骤,直到相交区域消失或相交区域内... 提出一种基于支持向量数据描述算法(SVDD)的多分类方法(S-MSVM)。受SVDD的启发,该方法对每类样本建立一个超球来界定,但训练好的超球在所有情况下都是相交的。选择相交区域的样本单独建立超球,重复该步骤,直到相交区域消失或相交区域内没有样本点。给出了该方法的时间复杂度分析,并通过实验验证了该方法具有相对较好的训练精度。 展开更多
关键词 支持向量数据描述算法 支持向量机多分类 分类器
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部