摘要
本文提出一种新型的手部姿态识别系统,用于控制多自由度假手。本系统利用FSR(Force Sensitive Resistor)传感器检测前臂肌肉的收缩和膨胀情况来实现不同动作的识别。通过前臂处的FSR传感器获取不同手部姿态对应的信号,经过支持向量机(Support Vector Machine)分类器分类后给出相应手部运动模式,这样使用者可以实现多自由度假手的控制。
本文建立假手运动模式识别及控制平台,此系统由三部分组成。首先,多通道FSR传感器信号采集系统实现前臂与系统之间的连接,为后续处理提供可靠的、有效的信号。上位机内信号分析处理试验系统,针对不同个体特点选择不同的传感器位置和数量、模式分类方法及最优参数模型,最大限度满足操作者需求。最后引入基于双DSP的假手控制系统,包括基于DSP2810的假手驱动与传感器系统和负责信号处理与决策的基于DSP2812的上层控制系统,彻底实现嵌入式控制,为假手的商业化做好准备。
对于多自由度假手的多模式控制,模式分类方法是核心内容。从实用的角度出发,尽量提高分类的快速性和保证高成功率。本文选择支持向量机这一模式分类方法,并针对假手控制特点讨论多类分类方法,引入基于量子粒子群的全局最优参数搜索方法,并通过实验证明其有效性。
为方便假手随身佩戴及嵌入式控制要求,介绍基于DSP2812的假手动作模式识别程序的设计思想及流程,系统的存储器配置和SPI接口的寄存器配置。算法程序设计分为三个部分,数据采集部分并加入采集过程中动作切换提示;SVM模型建立部分通过简化SVM的约束条件,实现样本训练过程在DSP中完成;分类预测部分,结合一对一方法,分别采用投票法和模糊法实现模式分类。
针对建立的多自由度仿人型假手系统,本文进行了大量的实验,实验结果为:在PC机中,根据训练难度将33种手部动作分为3类,按由易到难的顺序进行训练和分类,验证控制方式的有效性。在DSP中,利用10枚传感器,可以识别10种常用运动模式,并且成功率在95%以上。
In this thesis a new recognition system for hand gestures developed for the purpose of controlling active prosthesis hand is presented. The recognition system allows for the measurement and classification of muscle contraction around the lower arm. The singles obtained by the FSR sensors would be analyzed by the SVM divider, which is developed based on the theory of setting maximal distance between different categories, and then assigned to certain category. So the user can control the prosthesis through muscle contraction of the forearm according to different hand gestures.
The Multi-DOF prosthetic hand platform is constructed, which includes three parts. Firstly, the multi-channel acquisition system of FSR signals is established, which offer an interface between the human body and the system. Then, the analysis and processing system for experiment of FSR signals is founded. In this system, we can optimize the location and number of sensors; choose the most comfortable classification method and its parameters based on different operators to meet their demands. Lastly, a control system based on two DSP is also imported. The system contains the drive and sense system based on DSP2810 and the system based on DSP2812, which is used for management and decision-making. Preparing to be commercially produced, all of them can be achieved in DSP totally.
As for the control of Multi-DOF prosthetic, the method of classification is the core content. From the point of view of practical utility, the improvement of rapidity and success rate of classification is the main aim. The widely used method of SVM is also applied in this paper, in addition, the way of searching optimal parameters through QPSO are provided. In the end, experiments validate the effectiveness of the proposed method.
To meet needs of taking prosthetic hand every day, ideas and process of design for the prosthetic hand motion pattern recognition are introduced, which is used in embedded system .In the part of data acquisition, The configuration of SPI registers provided and the main program for sending and receiving are also introduced. As for the part of SVM model establishing, by simplifying the restrained conditions, the training can be accomplished in DSP. Lastly, by using one against one multi classification method, the class of test data is given through vote or fuzzy.
Based on the established prosthesis hand system, a lot of experiments are carried. The result indicates that, in the PC, the thirty three hand gestures are divided into three categories form the easiness to the difficulty, this kind of control method is validated a good one through training and classification; in the DSP, ten often used hand gestures can be recognized by ten sensors and the average success rate is above 95%.
引文
1.第二次全国残疾人抽样调查领导小组. 2006年第二次全国残疾人抽样调查主要数据公报.中华人民共和国国家统计局. 2006，(1)：1-2
2.刘志泉.我国肢体残疾人概况.中国康复医学杂志. 2003，(8)：493-494
3. Christopher Lake，John M.Miguelez. Evolution of Microprocessor Based Control Systems in Upper Extremity Prosthetics. Technology and Disability. 2003，(15):63-67
4. Biagiotti L，Lotti E，Melchiom C，et al. Mechatronics Design of Innovative Fingers for Anthropomorphic Robot Hands. Proceedings of the 2003 IEEE International Conference on Robotics and Automation，Taipei，2003:3187-3192
5.陈永华.脑电信号采集方法及其在假肢中的应用研究.大连理工大学硕士学位论文. 2005：3-10
6.Jonathan R，Wolpawa，Dennis J，et al. Brain-computer Interface for Communication and Control. Clinical Neurophysiology. 2002，113(1)：767-791
7.G.Pfurtscheller,C.Guger,G.Mueller. Brain Oscillations Control Hand Orthosis in a Tetraplegic. Neuroscience Letters . 2000，292：211-214
8. MUSSA-IVALDIS. Real Brains for Real Robots. Nature. 2000，408:305-306
9. Andtew B.Schwartz. Cortical Neural Prosthetics. Annu. Rev.Neurosci. 2004，27:487-507
10.赵京东.基于肌电信号的假手运动模式识别及控制系统的研究.哈尔滨工业大学博士学位论文.2006：1-22
11.WANG Gang，Ren Xiao-mei，WANG Zhi-zhong. Multifractal Analysisi osurface EMG Signals for Assessing Muscle Fatigue During Static Contractions. Journal of Zhejiang University SCIENCE.2007，8(6)：910-915
12. M. Bilodeau，S.Schindler-Ivens，D.M.William，R.Chandran，S.S.Sharma. EMG Frequency Content changes with Icreasing Force and During Fatigue in the Quadriceps Femoris Muscle of Man and Woman. Journal of Electromyography and Kinesiology. 2003，13：83-92
13. J.D. Zhao，H. Liu. Levenberg-Marquardt Based Neural Network Control for a Five-fingerd Prosthetic Hand. IEEE Conf. On Robotics and Automation，Barcelona，Spain，2005：4493~4498
14.罗志增，杨广映.基于触觉和肌电信号的假手模糊控制方法研究.机器人. 2006，28(2)：224-228
15.王人成，郑双喜.基于表面肌电信号的手指运动模式识别系统.康复医学工程. 2008，(5)：410-412
16.何乐生.基于肌电信号的人机接口技术的研究.东南大学博士学位论文.2006：2-10
17.李醒飞，史颖，杨晶晶.用肌电信号实时控制虚拟机械手臂.中国机械工程. 2006，(2)：187-195
18.高剑，罗志增.支持向量机在肌电信号模式识别中的应用.传感技术学报. 2007，(2)：366-369
19. Bitzer S，Smagt P. Learning EMG Control of a Robotic Hand: Towards Active Prostheses. Proceedings of the 2006 IEEE International Conference on Robotics and Automation，Orlando，2006:2819-2823
20.Y Su，A Wolczowski，M H Fisher，G D Bell. Towards an EMG Controlled Prosthetic Hand Using a 3D Electromagnetic Positioning System. Instrumentation and Measurement Technology Conference，Ottawa，Canada，2005：261-266
21. Force Sensing Resistor Integration Guide and Evaluation Parts Catalog. INTERLINK ELECTRONICS. http://www.interlinkelectronics.com
22.张今瑜，王岚，张立勋.基于多传感器的实时步态检测研究.哈尔滨工程大学学报. 2007，(2)：218-221
23. Bufu Huan，Meng Chen. Gait Event Detection with Intelligent Shoes. Proceedings of the 2007 International Conference on Information Acquisition. Jeju，korea，2007：579-584
24. Walter Dan Stiehl，Levi Lalla. A“Somatic Alphbet”Approach to“Sensitive Skin”. International Conference on Robotics & Automation，New Orleans，LA，2004: 2865-2870
25. Manjuladevi KUTTUVA，James.FLINT，Grigore BURDEA. Manipulation Practice for Upper-Limb Amputees Using Virtual Reality. PRESENCE. 2005，4(2) :175-182
26. Yuichiro Honda，Stefan Weber. Intelligent Recognition System for Hand Gesture. The 3th international IEEE EMBS Conference on Neural Engineering，Hawall，USA，2007：611-614
27. OliverAmft，HolgerJunker. Sensing Muscle Activities with Body-Worn Sensors. Proceedings of the International Workshop on Wearable and Implantable Body Sensor Networks，USA，2006：138-141
28. P.Lukowicz，F.Hanser，C.Szubski，W.Schobersberger.. Detecting andinterpreting muscle activity with wearable force sensors Pervasive. 2006，(6)：101-116
29. GeorgOgris，MatthiasKreil，Paul Lukowicz. Using FSR Based Muscle Activity Monitoring to Recognize Manipulative Arm Gestures. International Conference on Intelligent Robots and Systems，Portland，2007：45-48
30.胡仁喜. LabVIEW8.2.1虚拟仪器实例知道教程.机械工业出版社，2008：25-46
31.裴锋，杨万生. LabVIEW与Matlab混合编程.电子技术应用. 2004，(3):4-6
32.刘子民，何广军，白云，金凤杰.基于LabVIEW和Matlab的虚拟仪器设计与实现.弹道与制导学报. 2006，26(2)：788-790
33. Richard O，Duda Peter E.Hart.模式分类.李宏东.第2版.机械工业出版社，2006：45-62
34.邓乃扬，田英杰.数据挖掘中的新方法——支持向量机.科学出版社，2004：328-335
35. YUK YING CHUNG，ERIC H.C.CHOI，LIWEI LIU.A New Hybrid Audion Classification Algorithm Based on SVM Weight Factor and Eucilidean Distance. Proceeding of the 2007 WSEAS International Conference on Computer Engineering and Application，Gold Coast，Australia，2007：152-157
36.张覃铁.电子鼻：传感器阵列、系统机应用研究.华中科技大学博士学位论文. 2007：52-62
37.李云飞，黄彦全，蒋功连.基于PCA-SVM的电力系统短期负荷预测.电力系统及其自动化学报.2007，19(5)：66-70
38.薛薇. SPSS统计分析方法及应用.电子工业出版社，2004：326-340
39.方瑞明.支持向量机理论及其应用分析.中国电力出版社，2007：1-18
40.唐发明，王仲东，陈绵云.支持向量机多类分类算法研究.控制与决策. 2005，20(7)：746-754
41. Chih-Wei Hsu，Chih-Jen Lin. A Comparison of Methods for Multi-class Support Vector Machines. http://www.csie.ntu.edu.tw/~cjlin/libsvm
42.林梁升，刘志.基于RBF核函数的支持向量机参数选择.浙江工业大学学报.2007，35(2):163-167
43. CHAPELLE O，VAPINK V N. Choosing Multiple Parameters for Support Vector Machines. Machine Learning. 2002，46：131-159
44.曾建潮，介靖，崔志华.微粒群算法.科学出版社，2004：85-87
45. SUN Jun，XU Wenbo. A Global Search of Quantum-behaved Particle Swarm Optimization. Proc of IEEE Conference on Cybemetics and Intelligent Systems，Singapore，2004：111-116
46. Sun Jun，Feng Bin，XU Wenbo. Particle Swarm Optimization with Particle Having Quantum Behavior. Proc of Congress on Evolutionary Computation，San Diego，California，USA，2004:325-331
47.唐槐璐，须文波，龙海侠.基于量子行为的为例群优化算法的数据聚类.计算机应用研究. 2007，24(11)：49-51
48.苏奎峰，吕强，常天庆. TMS320X281X DSP原理及C程序开发.北京航空航天大学出版社，2008：73-85
49.贾伟，邵左文，张玉猛.基于SPI总线的高速串行数据采集系统设计. 2007，26(4)：37-40
50.李剑锋，佘龙华.基于双TMS320F28XX SPI的数据采集和处理.测控技术. 2005，24(6)：89-91
51.J.L.PONS, E.ROCON AND R.CERES，D.REYNAERTS，B.SARO. The MANUS-HAND Dextrous Robotics Upper Limb Prosthesis: Mechanical and Manipulation Aspects. Autonomous Robots. 2004，16：143-163
