基于状态转换机制的仿人型假手肌电控制方法  

A novel EMG controller for anthropomorphic prosthetic hands based on state switching mechanism

作　　者：姜力[1] 黄琦[1] 杨大鹏[1] 刘宏[1] 

机构地区：[1]机器人技术与系统国家重点实验室哈尔滨工业大学,哈尔滨150001

出　　处：《高技术通讯》2013年第12期1268-1274,共7页Chinese High Technology Letters

基　　金：国家自然科学基金(51205080;51175106);973计划(2011CB013306);机器人技术与系统国家重点实验室自主研究课题(SKLRS201201A03;SKLRS201201A01)资助项目

摘　　要：研究了在肌电控制信息不足的情况下,多自由度假手的肌电控制问题。基于抓取分类学和有限状态机(FSM)原理,通过抓取姿势与增量控制的状态切换,使人体通过2通道表面肌电信号控制假手实现了7种常用的抓取动作。实验结果表明,使用线性分类器(LDA)能有效地识别出手臂的肌肉收缩状态,使抓取成功率达到96%;使用肌肉收缩序列进行编码,可以快速地实现假手各工作状态的切换,使平均抓取时间小于20s,从而实现流利抓取。A study of electromyography （EMG） control for muhi-DOF prosthetic hands, under the circumstances of insuffi- cient EMG control information was carried out. Based on the knowledge of grasp taxonomy and the principle of finite state machine, seven widely used grasp patterns were realized on the prosthetic hand by extracting the control information from the two channel surface electromyography（EMG） signals and switching from the states of gesture coding and proportional controlling. The experiments were performed to evaluate both the grasp success rate and the average grasp time. The experimental results show that the method can effectively recognize the contraction patterns with the grasp success rate of 96% and the control state can be rapidly switched with the average grasp time less than 20 seconds, which in all ensures fluent hand grasps.

关 键 词：肌电控制 抓取分类学 有限状态机 假手 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]