DocumentCode :
2600498
Title :
Research on a detection and recognition method of tactile-slip sensation used to control the Elderly-assistant & Walking-assistant Robot
Author :
Wei, Xiaojuan ; Zhang, Xiaodong ; Wang, Yunxia
Author_Institution :
Sch. of Mech. Eng., Xi´´an Jiaotong Univ., Xi´´an, China
fYear :
2012
fDate :
20-24 Aug. 2012
Firstpage :
1040
Lastpage :
1045
Abstract :
In this paper, 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 and slip senses is proposed that used to control the Elderly-assistant & Walking-assistant Robot. First, on the basis of the proposed drive control system program of tactile and slip, detection system of tactile and slip senses is designed. And then, based on the tactile and slip feature representation and extraction, an improved classification and recognition method is proposed that K-nearest neighbor (KNN) algorithm are combined with K-means algorithm. In the end, through many online and offline experimental analysis, the results show that the tactile and slip senses detection and recognition method is effective, and it can realize the robot´s driving control.
Keywords :
handicapped aids; medical robotics; tactile sensors; K-means algorithm; K-nearest neighbor algorithm; KNN; detection method; drive control system program; elderly-assistant robot; offline experimental analysis; old people physical characteristics; online experimental analysis; recognition method; slip feature extraction; slip feature representation; tactile feature extraction; tactile feature representation; tactile-slip sensation; technical requirements; walking-assistant robot; Classification algorithms; Control systems; Educational institutions; Legged locomotion; Pattern recognition; Robot sensing systems;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Automation Science and Engineering (CASE), 2012 IEEE International Conference on
Conference_Location :
Seoul
ISSN :
2161-8070
Print_ISBN :
978-1-4673-0429-0
Type :
conf
DOI :
10.1109/CoASE.2012.6386341
Filename :
6386341
Link To Document :
بازگشت