基于触觉序列的物体分类

PDF下载HTML

Title:

Object classification based on the tactile sequence

作者:

马蕊^1,2,3, 刘华平^2,3, 孙富春^2,3, 高蒙¹

1. 石家庄铁道大学 电气与电子工程学院, 河北 石家庄 050043;
2. 清华大学 计算机科学与技术系, 北京 100084;
3. 清华大学 智能技术与系统国家重点实验室, 北京 100084

Author(s):

MA Rui^1,2,3, LIU Huaping^2,3, SUN Fuchun^2,3, GAO Meng¹

1. College of Electrical and Electronic Engineering, Shijiazhuang Railway University, Shijiazhuang 050043, China;
2. Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China;
3. State Key Laboratory of Intelligent Technology and System, Tsinghua University, Beijing 100084, China

关键词:

物体分类; 触觉序列; 线性动态系统; 系统包; 马丁距离; 支持向量机; K-Medoid算法

Keywords:

object classification; tactile sequence; linear dynamical system (LDS); bag-of-system; Martin distance; support vector machine (SVM); K-Medoid algorithm

分类号:

TP24

DOI:

10.3969/j.issn.1673-4785.201408026

文献标志码:

A

摘要:

通过安装触觉传感器的灵巧手对物体进行抓取,可以采集到丰富的触觉序列信息.对这些触觉信息进行分类可以显著提高机器人的环境感知和灵巧操作能力.为此,将触觉序列划分为一系列子触觉序列,使用基于线性动态系统(LDS)的方法进行特征提取.由于使用LDS提取的特征存在于非欧式空间,在对特征进行处理时,使用与欧式距离不同的马丁距离(Martin distance)作为量度来表征2个LDS特征之间的距离,并使用K-Medoid算法进行聚类.而后使用聚类得到的码书表征触觉序列,完成系统包(bag-of-system)特征模型构建,并利用支持向量机(SVM)实现高效分类.最后使用16种实验样本构建的触觉序列数据集对上述算法进行评测,获得了可观的识别效果,表明了该算法可以用于触觉序列的物体分类.

Abstract:

A large amount of information on tactile sequences can be collected by using a dexterous hand with a tactile sensor to grasp different objects. The abilities of a robot’s environmental perception and dexterous manipulation are significantly improved after these tactile sequences are classified. Therefore, tactile sequences are separated into a series of subgroups and features are extracted by using a method based on the linear dynamical system (LDS). Since the features extracted by LDS are located in the non-Euclidean space, when dealing with these features, the Martin distance which is a measurement different from Euclidean distance is applied to represent the distance between two LDS features, and the K-Medoid algorithm is used for clustering. Then, the codebook which is formed after clustering is used to represent the tactile sequence, the model of bag-of-system is formed, and the support vector machine (SVM) is used to classify these objects efficiently. Finally, a dataset based on 16 objects is used to evaluate the algorithm and the result of recognition is good, which proves this algorithm can be used in tactile sequences for object classification.