Human-Machine Interaction Control Based on Force Myograph andElectrical Stimulation Sensory Feedback for Multi-DOF Robotic Hand
LI Nan1, LIU Bo1, HUO Hong1, YE Yuxuan1, JIANG Li2
1. Beijing Aerospace Automatic Control Institute, Beijing 100854, China;
2. State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150086, China
李楠, 刘波, 霍宏, 叶玉璇, 姜力. 基于肌力信号与电刺激感觉反馈的多自由度机械手人机交互控制[J]. 机器人, 2015, 37(6): 718-724.DOI: 10.13973/j.cnki.robot.2015.0718.
LI Nan, LIU Bo, HUO Hong, YE Yuxuan, JIANG Li. Human-Machine Interaction Control Based on Force Myograph andElectrical Stimulation Sensory Feedback for Multi-DOF Robotic Hand. ROBOT, 2015, 37(6): 718-724. DOI: 10.13973/j.cnki.robot.2015.0718.
A wearable bi-directional human-machine interaction(HMI) system and its control methods are proposed to enable the user to control multi-DOF robotic hand freely and feel the gripping force from the robotic hand. A force sensory resistor(FSR) array is built to measure the forearm force myographic(FMG) signals corresponding to different hand motions of the user. A multiclass classifier is designed based on the support vector machine(SVM) algorithm to recognize the hand motions and generate motion codes to control the robotic hand movements. Moreover, sensory feedback is achieved by transforming the gripping force signals of the robotic hand into electrical stimulation signals of skin based on the principle of transcutaneous electrical nerve stimulation(TENS). Experimental results show that the motion mode recognition method based on FMG and SVM can identify 10 typical hand motions with the accuracy of above 95%. The electrical stimulation method can feed back the perception of gripping force to the body accurately and help the user to grip objects without vision.
[1] 樊绍巍,刘伊威,金明河,等.HIT/DLR Hand Ⅱ类人形五指灵巧手机构的研究[J].哈尔滨工程大学学报,2009,30(2):171-177.Fan S W, Liu Y W, Jin M H, et al. Research on the mechanics of the HIT/DLR hand II anthropomorphic five-finger dexterous hand[J]. Journal of Harbin Engineering University, 2009, 30(2):171-177.[2] Johannes M S, Bigelow J D, Burck J M, et al. An overview of the developmental process for the modular prosthetic limb[J]. Johns Hopkins APL Technical Digest, 2011, 30(3):207-216.[3] Doggett W R, Dorsey J T, Jones T C, et al. Development of a tendon-actuated lightweight in-space manipulator[C]//42nd Aerospace Mechanisms Symposium. Hampton, USA:NASA, 2014:1-14.[4] Feng F, Liu Y W, Liu H, et al. Development of space end-effector with capabilities of misalignment tolerance and soft capture based on tendon-sheath transmission system[J]. Journal of Central South University, 2013, 20(11):3015-3030. [5] Carey M W, Kurz E M, Matte J D, et al. Novel EOD robot design with dexterous gripper and intuitive teleoperation[C]//World Automation Congress. Piscataway, USA:IEEE, 2012:1-6.[6] 曾建军,杨汝清,张伟军.有限人参与下的排爆机器人半自主抓取[J].上海交通大学学报,2007,41(8):1238-1243.Zeng J J, Yang R Q, Zhang W J. Research of semi-automatic bomb fetching with limited support of human in explosive ordnance disposal robot[J]. Journal of Shanghai Jiaotong University, 2007, 41(8):1238-1243.[7] 李楠,赵京东,姜力,等.多自由度仿生假手嵌入式控制系统及其抓取策略[J].机器人,2011,33(1):22-27.Li N, Zhao J D, Jiang L, et al. Embedded control system for multi-DOF anthropomorphic prosthetic hand and its grasping strategy[J]. Robot, 2011, 33(1):22-27.[8] Dalley S A, Varol H A, Goldfarb M. A method for the control of multigrasp myoelectric prosthetic hands[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2012, 20(1):58-67. [9] 王家顺,王田苗,魏军,等.一种面向遥操作的新型数据手套研制[J].机器人,2000,22(3):201-206.Wang J S, Wang T M, Wei J, et al. Development of a new telemanipulation-oriented data glove[J]. Robot, 2000, 22(3):201-206.[10] Fang H G, Xie Z W, Liu H. An exoskeleton master hand for controlling DLR/HIT hand[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2009:3703-3708.[11] Yang D P, Zhao J D, Gu Y K, et al. An anthropomorphic robot hand developed based on underactuated mechanism and controlled by EMG signals[J]. Journal of Bionic Engineering, 2009, 6(3):255-263. [12] Tenore F V G, Ramos A, Fahmy A, et al. Decoding of individuated finger movements using surface electromyography[J]. IEEE Transactions on Biomedical Engineering, 2009, 56(5):1427-1434. [13] Honda Y, Weber S, Lueth T C. Intelligent recognition system for hand gestures[C]//3rd International IEEE/EMBS Conference on Neural Engineering. Piscataway, USA:IEEE, 2007:611-614.[14] Fang H G, Xie Z W, Liu H, et al. An exoskeleton force feedback master finger distinguishing contact and non-contact mode[C]//IEEE/ASME International Conference on Advanced Intelligent Mechatronics. Piscataway, USA:IEEE, 2009:1059-1064.[15] 袁明.肌电仿生控制与遥操作研究[D].杭州:杭州电子科技大学,2012.Yuan M. Myoelectric bionic control and tele-operation research[D]. Hangzhou:Hangzhou Dianzi University, 2012.[16] 梅旭红.基于网络和无线传输的机器人肌电控制[D].杭州:杭州电子科技大学,2012.Mei X H. The SEMG control of telerobot based on network and wireless[D]. Hangzhou:Hangzhou Dianzi University, 2012.[17] Blum J E. Using force sensors to effectively control a below-elbow intelligent prosthetic device[EB/OL].(2012-03-31)[2015-04-18]. http://jeremyblum.com/wp-content/uploads/2008/11/CONTROLLING-AN-INTELLIGENT-PROSTHETIC-DEVICE.pdf.[18] Kaczmarek K A, Webster J G, Bachyrita P, et al. Electrotactile and vibrotactile displays for sensory substitution systems[J]. IEEE Transactions on Biomedical Engineering, 1991, 38(1):1-16. [19] McNeal D R. Analysis of a model for excitation of myelinated nerve[J]. IEEE Transactions on Biomedical Engineering, 1976, 23(4):329-337.[20] Hsu C W, Lin C J. A comparison of methods for multiclass support vector machines[J]. IEEE Transactions on Neural Net- works, 2002, 13(2):415-425. [21] Englehart K, Hudgins B. A robust, real-time control scheme for multifunction myoelectric control[J]. IEEE Transactions on Biomedical Engineering, 2003, 50(7):848-854.
