5指仿人假手及模式识别控制的研究  

Research on a five-fingered prosthetic hand and controlledby pattern recognition method

作　　者：王新庆[1] 刘伊威[1] 孙超[1] 刘宏[1] 

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

出　　处：《华中科技大学学报（自然科学版）》2010年第12期109-112,共4页Journal of Huazhong University of Science and Technology(Natural Science Edition)

基　　金：国家高技术研究发展计划资助项目(2009AA043803);国家自然科学基金重点资助项目(50435040)

摘　　要：基于生物机电一体化方法设计了带有感觉反馈功能的5指假手系统;假手本体具有类似人手的弧形掌面,通过耦合连杆机构实现5指的独立驱动,并在手指内部集成了力矩及位置传感器,从而有效提高了外观、运动形式的仿人性及操作的灵活性.以FSR传感器检测前臂肌肉压力信号为控制源,经过支持向量机SVM分类器实现手部运动模式的识别,采用相关系数与主成分分析相结合的方法优化了传感器的位置及数量,此外针对SVM以及最近邻法进行了10种运动模式的对比试验,结果表明手指的运动形式仿人度高,灵活性高,且SVM的识别成功率要高于近邻法.The five-fingered prosthetic hand with sensory feed-back system is developed;the cambered palm is specially designed,each finger could fulfill flexion and extension through coupling link mechanism.Besides,each finger is equipped with torque and position sensors.Thus,the cosmetics and dexterity is improved remarkably compared to commercial prosthesis.By taken the pressure of muscles as source of control,the intention of human could be realized through pattern reorganization method,the quantity and array of force sensitive resistors（FSR） sensors are optimized combining correlation coefficient analysis and principal component analysis.The experiment revealed that the hand is dexterous and manipulates like human.Compared to nearest neighborhood classifier,support vector machine（SVM） method improves the predict success rate.

关 键 词：模式识别 支持向量机 假手 耦合连杆 力敏电阻 主成分分析 相关系数 

分 类 号：TP241.3[自动化与计算机技术—检测技术与自动化装置]