Knee-joint exoskeleton control based on data-driven approach

doi:10.3785/j.issn.1008-973X.2019.10.020

Journal of ZheJiang University (Engineering Science)

2019, Vol. 53

Issue (10): 2024-2033 DOI: 10.3785/j.issn.1008-973X.2019.10.020

Automation Technology, Computer Technology

Knee-joint exoskeleton control based on data-driven approach

Yan ZHANG(

),Jian-zhou WANG,Wei LI,Jie WANG*(

),Ling-ling CHEN,Peng YANG

School of Artificial Intelligence, Hebei University of Technology, Tianjin 300131, China

Download:

HTML

PDF(1584KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

The two-dimensional laser rangefinder was used to collect terrain data for online identification in order to identify human movement intentions and coordinate human-exoskeleton motion. The method of learning vector quantization (LVQ) was used based on the distance features between different terrains in order to achieve fast and accurate terrain classification. A model-free adaptive control method based on data drive was designed, and the dynamic linearization model was established based on the input and output data of knee joint angle, which avoided the complexity and error of human-exoskeleton modeling. A human-exoskeleton model was established and the prior torque of the knee joint was obtained through the walking simulation. The prior torque was introduced to improve the accuracy of the controller. The ADAMS-MATLAB co-simulation platform was constructed, and the flat road condition was selected for experiment. The experimental results show that the designed strategy enables the knee-joint exoskeleton to track the trajectory of angle well and has a good performance on walking assistance.

Key words： exoskeleton terrain recognition data-driven model-free adaptive control dynamics simulation

Received: 23 August 2018 Published: 30 September 2019

CLC:

TP 242

Corresponding Authors: Jie WANG E-mail: yzhangz@163.com;wangjie@hebut.edu.cn

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Yan ZHANG
	Jian-zhou WANG
	Wei LI
	Jie WANG
	Ling-ling CHEN
	Peng YANG

Cite this article:

Yan ZHANG,Jian-zhou WANG,Wei LI,Jie WANG,Ling-ling CHEN,Peng YANG. Knee-joint exoskeleton control based on data-driven approach. Journal of ZheJiang University (Engineering Science), 2019, 53(10): 2024-2033.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2019.10.020 OR http://www.zjujournals.com/eng/Y2019/V53/I10/2024

基于数据驱动的膝关节外骨骼控制

为了识别人体运动意图协调人机运动，采用二维激光测距仪采集地形数据进行在线识别，使用学习向量量化（LVQ）的方法，基于不同地形间的距离特征实现快速、准确的地形分类. 设计基于数据驱动的无模型自适应控制方法，基于膝关节角度的输入输出数据建立动态线性化模型，避免了人机外骨骼建模的复杂性和建模误差. 建立人机外骨骼模型，通过仿真得到正常行走时膝关节的先验力矩，引入先验力矩提高控制器的准确性. 搭建ADAMS和MATLAB联合仿真平台，选取平地路况进行实验. 实验结果表明，所设计的控制方法使得外骨骼膝关节对目标角度有良好的跟踪，对人体行走有较好的助行效果.

关键词： 外骨骼, 地形识别, 数据驱动, 无模型自适应控制, 动力学仿真

Fig.1 Control block diagram of knee-joint exoskeleton

Fig.2 Two-dimensional laser scanning rangefinder

Tab.1 Parameters of two-dimensional laser sensor

Fig.3 Scanning range and recognition distance of sensors

Fig.4 Location of marker and VICON gait analysis system

Fig.5 Five terrain data collected by sensor

Fig.6 Human lower limb and exoskeleton model

Fig.7 Simulation prior torque of knee joint

Tab.2 Comparison of recognition rates of four methods

Fig.8 Comparison of average recognition time of four methods

Tab.3 Parameters of human model

Fig.9 Angle-driven simulation of human gait diagram

Fig.10 Comparison of desired and simulated hip joint angles

Fig.11 Comparison of desired and simulated knee joint angles

Fig.12 Comparison of desired and simulated ankle joint angles

Fig.13 Simulation gait diagram of wearing exoskeleton

Fig.14 Comparison of knee angle tracking performance between MFAC combined prior torque and MFAC methods

Fig.15 Comparison of knee angle tracking error between MFAC combined prior torque and MFAC methods

Fig.16 Comparison of simulation prior torque and control torque


[1]	KAZEROONI H, STEGER R The Berkeley lower extremity exoskeleton[J]. Journal of Dynamic Systems, Measurement and Control, 2006, 128 (1): 14- 25 doi: 10.1115/1.2168164

[2]	WALSH C J, ENDO K, HERR H A quasi-passive leg exoskeleton for load-carrying augmentation[J]. International Journal of Humanoid Robotics, 2007, 4 (3): 487- 506 doi: 10.1142/S0219843607001126

[3]	TSUKAHARA A, HASEGAWA Y, EGUCHI K, et al Restoration of gait for spinal cord injury patients using HAL with intention estimator for preferable swing speed[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2015, 23 (2): 308- 318 doi: 10.1109/TNSRE.2014.2364618

[4]	杨巍, 张秀峰, 杨灿军, 等基于人机5杆模型的下肢外骨骼系统设计[J]. 浙江大学学报: 工学版, 2014, 48 (3): 430- 435 YANG Wei, ZHANG Xiu-feng, YANG Can-jun, et al Design of a lower extremity exoskeleton based on 5-bar human machine model[J]. Journal of Zhejiang University: Engineering Science, 2014, 48 (3): 430- 435

[5]	刘磊, 杨鹏, 刘作军基于多源信息和广义回归神经网络的下肢运动模式识别[J]. 机器人, 2015, 37 (3): 310- 317 LIU Lei, YANG Peng, LIU Zuo-jun Lower limb locomotion modes recognition based on multiple-source information and general regression neural network[J]. Robot, 2015, 37 (3): 310- 317

[6]	KRAUSZ N E, LENZI T, HARGROVE L J Depth sensing for improved control of lower limb prostheses[J]. IEEE Transactions on Biomedical Engineering, 2015, 62 (11): 2576- 2587 doi: 10.1109/TBME.2015.2448457

[7]	路永乐, 张欣, 龚爽, 等基于MEMS惯性传感器的人体多运动模式识别[J]. 中国惯性技术学报, 2016, 24 (5): 589- 594 LU Yong-le, ZHANG Xin, GONG Shuang, et al Recognition of multiple human motion patterns based on MEMS inertial sensors[J]. Journal of Chinese Inertial Technology, 2016, 24 (5): 589- 594

[8]	张燕, 许京, 陈玲玲, 等基于激光距离传感器的路况识别系统的设计[J]. 激光与红外, 2016, 46 (3): 265- 270 ZHANG Yan, XU Jing, CHEN Ling-ling, et al Design of terrain recognition system based on laser distance sensor[J]. Laser and Infrared, 2016, 46 (3): 265- 270 doi: 10.3969/j.issn.1001-5078.2016.03.004

[9]	肖熙, 周路基于k均值和基于归一化类内方差的语音识别自适应聚类特征提取算法法[J]. 清华大学学报: 自然科学版, 2017, 57 (8): 857- 861 XIAO Xi, ZHOU Lu Speech recognition adaptive clustering feature extraction algorithms based on the k-means algorithm and the normalized intra-class variance[J]. Journal of Tsinghua University: Science and Technology, 2017, 57 (8): 857- 861

[10]	PRATT J E, KRUPP B T, MORSE C J, et al. The RoboKnee: an exoskeleton for enhancing strength and endurance during walking [C]//IEEE International Conference on Robotics and Automation. New Orleans: IEEE, 2004: 2430-3435.

[11]	RIFAI H, MOHAMMED S, DJOUANI K, et al Toward lower limbs functional rehabilitation through a knee-joint exoskeleton[J]. IEEE Transactions on Control Systems Technology, 2017, 25 (2): 712- 719 doi: 10.1109/TCST.2016.2565385

[12]	CHEN X, ZENG Y, YIN Y H Improving the transparency of an exoskeleton knee joint based on the understanding of motor intent using energy kernel method of EMG[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2017, 25 (6): 577- 588 doi: 10.1109/TNSRE.2016.2582321

[13]	韩亚丽, 许有熊, 高海涛, 等基于导纳控制的膝关节外骨骼摆动控制研究[J]. 自动化学报, 2016, 42 (12): 1944- 1950 HAN Ya-li, XU You-xiong, GAO Hai-tao, et al Knee joint exoskeleton swing control with admittance control[J]. Acta Automatica A Sinica, 2016, 42 (12): 1944- 1950

[14]	ZHU Y M, HOU Z S, QIAN F, et al Dual RBFNNs-based model-free adaptive control with aspen HYSYS simulation[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28 (3): 759- 765 doi: 10.1109/TNNLS.2016.2522098

[15]	BU X H, HOU Z S, ZHANG H W Data-driven multiagent systems consensus tracking using model free adaptive control[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29 (5): 1514- 1524 doi: 10.1109/TNNLS.2017.2673020

[16]	XU D Z, SHI Y, JI Z C Model-free adaptive discrete-time integral sliding-mode-constrained-control for autonomous 4WMV parking systems[J]. IEEE Transactions on Industrial Electronics, 2018, 65 (1): 834- 843 doi: 10.1109/TIE.2017.2739680

[17]	WANG Z W, NASSER M N, HUANG T S Spatial-spectral classification of hyperspectral images using discriminative dictionary designed by learning vector quantization[J]. IEEE Geoscience and Remote Sensing Society, 2013, 52 (8): 4808- 4822

[18]	YANG H T, HUANG C M, HUANG Y C, et al A weather-based hybrid method for 1-day ahead hourly forecasting of PV power output[J]. IEEE Transactions on Sustainable Energy, 2014, 5 (3): 917- 926 doi: 10.1109/TSTE.2014.2313600

[19]	EKRAMIAN M, SHEIKHOLESLAM F, HOSSEINNIA S, et al Adaptive state observer for lipschitz nonlinear systems[J]. Systems and Control Letters, 2013, 62 (4): 319- 323 doi: 10.1016/j.sysconle.2013.01.002

[20]	HOU Z S, JIN S T Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems[J]. IEEE Transactions on Neural Networks, 2011, 22 (12): 2173- 2188 doi: 10.1109/TNN.2011.2176141

[21]	HOU Z S, ZHU Y M Controller-dynamic-linearization- based model free adaptive control for discrete-time nonlinear systems[J]. IEEE Transactions on Industrial Informatics, 2013, 9 (4): 2301- 2309 doi: 10.1109/TII.2013.2257806

[22]	HOU Z S, JIN S T A novel data-driven control approach for a class of discrete-time nonlinear systems[J]. IEEE Transactions on Control Systems Technology, 2011, 19 (6): 1549- 1558 doi: 10.1109/TCST.2010.2093136

[23]	黄萍, 钟慧敏, 陈博正常青年人三维步态: 时空及运动学和运动力学参数分析[J]. 中国组织工程研究, 2015, 19 (24): 3882- 3888 HUANG Ping, ZHONG Hui-min, CHEN Bo Three- dimensional gait analysis in normal young adults: temporal, kinematic and mechanical parameters[J]. Chinese Journal of Tissue Engineering Research, 2015, 19 (24): 3882- 3888 doi: 10.3969/j.issn.2095-4344.2015.24.021

[1]	Can-jun YANG,Zhen-zhe PENG,Ling-hui XU,Wei YANG. Design of flexible knee-joint protection exoskeleton and walking assistance method[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(2): 213-221.

[2]	You-kang DUAN,Xiao-gang CHEN,Jian GUI,Bin MA,Shun-fen LI,Zhi-tang SONG. Continuous kinematics prediction of lower limbs based on phase division[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(1): 89-95.

[3]	ZHANG Ming-kui, CHENG Wen-ming, LIU Fang. Coupling effect between load characteristics and joint driving characteristics of powered exoskeleton[J]. Journal of ZheJiang University (Engineering Science), 2017, 51(4): 807-816.

[4]	SONG Xiao-xuan, FENG Tian-heng, HUANG Ping-jie, HOU Di-bo, ZHANG Guang-xin. Sudden water pollution simulation method based on dynamic data-driven techniques[J]. Journal of ZheJiang University (Engineering Science), 2015, 49(1): 63-68.

[5]	YAN Hua, YANG Can-jun, CHEN Jie. Optimal design on shoulder joint of upper limb exoskeleton robot for motor rehabilitation and system application[J]. Journal of ZheJiang University (Engineering Science), 2014, 48(6): 1086-1094.

[6]	YANG Wei, ZHANG Xiu-feng, YANG Can-jun, WU Hai-jie. Design of a lower extremity exoskeleton based on 5-bar human machine model[J]. Journal of ZheJiang University (Engineering Science), 2014, 48(3): 430-435.

[7]	YANG Zhong-liang, TANG Zhi-chuan, CHEN Yu-miao, GAO Zeng-gui. Force-sEMG relations recognition models of forearm exoskeleton for bilateral training[J]. Journal of ZheJiang University (Engineering Science), 2014, 48(12): 2152-2161.

[8]	YAN Hua, YANG Can-jun, CHEN Jie. Optimal design on shoulder joint of upper limb exoskeleton robot for motor rehabilitation and system application[J]. Journal of ZheJiang University (Engineering Science), 2014, 48(1): 0-00.

[9]	ZHAO Zhen,ZHANG Shu-you. Study of the electromagnetic-dynamics interaction of the breaking process of low-voltage molded case circuit breaker[J]. Journal of ZheJiang University (Engineering Science), 2011, 45(11): 1913-1921.

Viewed

Full text

Abstract

Cited

Shared

Discussed