Abstract：As a significant aspect of human-computer interaction, gait recognition technology has a broad prospect in robot control area. A method for intelligent robot cooperative control system was proposed by using single leg surface EMG-based gait recognition technology. The system achieved the classification and recognition among four different gaits (moving forward, moving backward, turning left and turning right) by using mutual information based minimal-redundancy-maximal-relevance (MRMR) algorithm, and built up a synchronous robot control system. Surface EMG (sEMG) signals were collected from 8 subjects to classify and recognize the gait, and then the recognition result was used to control the robot synchronous motion. The results of the experiment showed that the recognition accuracy of the system reached to 88%. Based on the proposed approach, a robot synchronous control system with good synchronous controlling performance and high controlling accuracy was built. In concusion, the leg EMG signal based robot cooperative control technology has the application potentials in the areas of civilian equipment control and human-computer interaction in the future.
[1] Hatanaka T, Chopra N, Spong MW. Passivity-based control of robots: Historical perspective and contemporary issues[C]//2015 IEEE 54th Annual Conference on Decision and Control (CDC). Osaca: IEEE, 2015: 2450-2452. [2] Pham H, Kawanishi M, Narikiyo T. A LLE-HMM-based framework for recognizing human gait movement from EMG [C]// 2015 IEEE International Conference on Robotics and Automation (ICRA). Seattle: IEEE, 2015: 2997-3002. [3] Zhang TY. The research on motion recognition based on EMG of residual thigh [C]//Bioinformatics and Biomedical Engineering: New Advances: Proceedings of the 9th International Conference on Bioinformatics and Biomedical Engineering (iCBBE 2015), Shanghai: CRC Press, 2015: 445. [4] Hargrove LJ, Simon AM, Young AJ, et al. Robotic leg control with EMG decoding in an amputee with nerve transfers [J]. New England Journal of Medicine, 2013, 369(13): 1237-1242. [5] Fa-rong G, Jia-jia W, Xu-gang X, et al. Gait recognition for lower extremity electromyographic signals based on PSO-SVM method [J]. Journal of Electronics & Information Technology, 2015, 5: 022. [6] Peng H, Long F, Ding C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8): 1226-1238. [7] Linder T, Arras KO. People detection, tracking and visualization using ROS on a mobile service robot [M]//Robot Operating System (ROS). Beilin: Springer International Publishing, 2016: 187-213. [8] Quigley M, Conley K, Gerkey B, et al. ROS: an open-source Robot Operating System [C]//ICRA Workshop on Open Source Software. Kobe:IEEE, 2009, 3(3.2): 5. [9] Huang H, Kuiken TA, Lipschutz RD. A strategy for identifying locomotion modes using surface electromyography [J]. IEEE Transactions on Biomedical Engineering, 2009, 56(1): 65-73. [10] Rainoldi A, Melchiorri G, Caruso I. A method for positioning electrodes during surface EMG recordings in lower limb muscles [J]. Journal of Neuroscience Methods, 2004, 134(1): 37-43. [11] 张旭. 基于表面肌电信号的人体动作识别与交互 [D]. 合肥:中国科学技术大学, 2010. [12] 陈玲玲. 基于支持向量机的下肢肌电信号模式识别的研究 [D]. 天津: 河北工业大学, 2006. [13] Haroon N, Malik AN. Multiple hand gesture recognition using surface EMG signals [J]. Journal of Biomedical Engineering and Medical Imaging, 2016, 3(1): 1-8. [14] Chen X, Zhang X, Zhao Z Y, et al. Multiple hand gesture recognition based on surface EMG signal [C]// The 1st International Conference on Bioinformatics and Biomedical Engineering. Wuhan: IEEE, 2007: 506-509. [15] Kosmidou VE, Hadjileontiadis LJ. Sign language recognition using intrinsic-mode sample entropy on sEMG and accelerometer data [J]. IEEE Transactions on Biomedical Engineering, 2009, 56(12): 2879-2890. [16] 成娟. 基于表面肌电和加速度信号融合的动作识别和人体行为分析研究 [D]. 合肥:中国科学技术大学, 2013. [17] 佟丽娜, 侯增广, 彭亮,等. 基于多路sEMG时序分析的人体运动模式识别方法 [J]. 自动化学报, 2014, 40(5): 810-821. [18] Wang N, Chen Y, Zhang X. Realtime recognition of multi-finger prehensile gestures [J]. Biomedical Signal Processing and Control, 2014, 13: 262-269. [19] 刘欣. 基于模式识别的肌电信号动作分类性能研究 [D]. 济南:山东大学, 2010. [20] 王红旗, 李林伟, 毛啊敏. 基于小波包的表面肌电信号特征表示与识别 [J]. 计算机工程与应用, 2015,51(9):217-220. [21] Kwak N, Choi CH. Input feature selection by mutual information based on Parzenwindow [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(12): 1667-1671. [22] Chen L, Yang P, Xu X, et al. Fuzzy support vector machine for EMG pattern recognition and myoelectrical prosthesis control [M]//Advances in Neural Networks-ISNN 2007. Beilin:Springer Berlin Heidelberg, 2007: 1291-1298. [23] 刘品杰. ROS机器人程序设计 [M]. 北京: 机械工业出版社, 2014.
