用于助老助行机器人驱动控制的触滑觉检测识别方法  

Detection and recognition method of tactile-slip sensation for elderly-assistant & walking-assistant robot

作　　者：魏晓娟[1] 张小栋[2] 

机构地区：[1]西北民族大学电气工程学院,兰州730124 [2]西安交通大学机械工程学院,西安710049

出　　处：《计算机应用》2014年第A01期156-158,共3页journal of Computer Applications

基　　金：国家自然科学基金资助项目(61263002;61174067)

摘　　要：针对老年人的生理特征,以及其对操作助行机器人的舒适度和掌控感的技术需求,提出一种用于助老助行机器人驱动控制的触滑觉检测识别方法。首先,在提出助老助行机器人触滑觉驱动控制系统方案的基础上,设计开发了助老助行机器人系统;进而,研究讨论了用于驱动控制模式识别的触滑觉信号的特征表示与提取方法,提出一种采用聚类中的K-均值和分类中的K近邻算法相结合的改进分类识别方法;最后,通过大量的在线及离线实验分析,结果表明:所研究的触滑觉检测识别方法是有效的,它能够实现助老助行机器人的触滑觉驱动控制。According to the old people＇s physical characteristics and their technical requirements for comfort and mastery when operating the robot, a detection and recognition method of tactile-slip sensations was proposed to control the elderly- assistant ＆ walking-assistant robot. First, on the basis of the proposed drive control system program of tactile and shp, the elderly-assistant ＆ walking-assistant robot was designed. Then based on the tactile and slip feature representation and extraction, an improved classification and recognition method was proposed using K-Nearest Neighbor （KNN） algorithm and K-means algorithm. In the end, through many online and oitline experimental analysis, the results show that the tactile and slip sensation detection and recognition method is effective, and it can realize the robot＇s driving control.

关 键 词：触滑觉传感器 聚偏氟二烯 模式识别 助老助行机器人 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]