TRANSITION MOTION PATTERN CLASSIFICATION FOR LOWER LIMB EXOSKELETON IN STAIR SCENES BASED ON CNN AND GRU

被引:0
|
作者
Yu, Fangli [1 ,2 ]
Zheng, Jianbin [1 ]
Yu, Lie [3 ]
Xiao, Hui [2 ]
Chen, Qiang [2 ]
Zhang, Di [2 ]
机构
[1] Wuhan Univ Technology, Sch Informat Engn, 122 Luoshi Rd, Wuhan, Hubei, Peoples R China
[2] Peoples Liberat Army AF Early Warning Acad, 288 Huangpu Rd, Wuhan, Hubei, Peoples R China
[3] Wuhan Text Univ, Sch Elect & Elect Engn, Wuhan, Hubei, Peoples R China
基金
中国国家自然科学基金;
关键词
Motion pattern classification; lower limb exoskeleton; CNN; GRU; LSTM-CNN;
D O I
10.1142/S0219519423500859
中图分类号
Q6 [生物物理学];
学科分类号
071011 ;
摘要
Motion pattern classification is one of the important research fields in lower extremity exoskeleton robot, it refers to acquiring motion data from multiple sensors installed on the exoskeleton. We designed a wearable lower limb exoskeleton robot with multiple sensors mainly including force sensitive resistors (FSRs) inside smart shoes and encoders inside joints. The wearable robot was used to help people carry the heavy load in the scenes of ascending stairs and descending stairs. The experiments of stair walking were carried out by the subjects who wore the exoskeleton to ascend stairs and descend stairs for a designated time. Before or after the stair walking, the subject would turn to move on flat ground with the result that there existed four transition motions between the stair and flat ground walking. As known, there is less research focusing on the classification of transition motions. The aim of this paper is to classify these motion patterns through a learning algorithm. The convolutional neural network (CNN) and gated recurrent unit (GRU) framework were combined to improve the classification accuracy. Specifically, CNN was used to extract the features of the motion pattern, while GRU was used to extract the temporal correlation during walking. Experimental works showed that the proposed CNN-GRU possessed a significantly high prediction accuracy in motion pattern classification. Compared with CNN, GRU and LSTM-CNN models whose accuracy score does not exceed 93.22%, the proposed CNN-GRU gained a high accuracy of 95.51%.
引用
收藏
页数:20
相关论文
共 50 条
  • [1] Motion Adaption and Trajectory Generation of Stair Ascent and Descent with a Lower Limb Exoskeleton for Paraplegics
    Zhong, Chun-Hao
    Zhao, Xuan
    Liang, Feng-Yan
    Ma, Hao
    Liao, Wei-Hsin
    [J]. 2019 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS (AIM), 2019, : 612 - 617
  • [2] A Novel Gait Pattern Recognition Method Based on LSTM-CNN for Lower Limb Exoskeleton
    Chao-feng Chen
    Zhi-jiang Du
    Long He
    Yong-jun Shi
    Jia-qi Wang
    Wei Dong
    [J]. Journal of Bionic Engineering, 2021, 18 : 1059 - 1072
  • [3] A Novel Gait Pattern Recognition Method Based on LSTM-CNN for Lower Limb Exoskeleton
    Chen, Chao-feng
    Du, Zhi-jiang
    He, Long
    Shi, Yong-jun
    Wang, Jia-qi
    Dong, Wei
    [J]. JOURNAL OF BIONIC ENGINEERING, 2021, 18 (05) : 1059 - 1072
  • [4] Preliminary evaluation of a lower-limb exoskeleton - stair climbing
    Chandrapal, Mervin
    Chen, XiaoQi
    Wang, Wenhui
    [J]. 2013 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS (AIM): MECHATRONICS FOR HUMAN WELLBEING, 2013, : 1458 - 1463
  • [5] Characteristics of a Lower Limb Exoskeleton for Gait and Stair Climbing Therapies
    Elias, Dante A.
    Cerna, Diego
    Chicoma, Christian
    Mio, Renato
    [J]. INTERDISCIPLINARY APPLICATIONS OF KINEMATICS, 2019, 71 : 81 - 92
  • [6] Design and fabrication of a lower limb exoskeleton to assist in stair ascending
    Joudzadeh, Payman
    Hadi, Alireza
    Tarvirdizadeh, Bahram
    Borooghani, Danial
    Ahpour, Khalil
    [J]. INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION, 2019, 46 (02): : 290 - 299
  • [7] Learning and planning of stair ascent for lower-limb exoskeleton systems
    Chen, Qiming
    Cheng, Hong
    Huang, Rui
    Qiu, Jing
    Chen, Xinhua
    [J]. INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION, 2019, 46 (03): : 421 - 430
  • [8] Adaptive Stair-Ascending and Stair-Descending Strategies for Powered Lower Limb Exoskeleton
    Xu, Fashu
    Lin, Xichuan
    Cheng, Hong
    Huang, Rui
    Chen, Qiming
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION (ICMA), 2017, : 1579 - 1584
  • [9] Stair-ascent strategies and performance evaluation for a lower limb exoskeleton
    Fashu Xu
    Rui Huang
    Hong Cheng
    Jing Qiu
    Shiqiang Xiang
    Congbin Shi
    Wenhao Ma
    [J]. International Journal of Intelligent Robotics and Applications, 2020, 4 : 278 - 293
  • [10] Stair-ascent strategies and performance evaluation for a lower limb exoskeleton
    Xu, Fashu
    Huang, Rui
    Cheng, Hong
    Qiu, Jing
    Xiang, Shiqiang
    Shi, Congbin
    Ma, Wenhao
    [J]. INTERNATIONAL JOURNAL OF INTELLIGENT ROBOTICS AND APPLICATIONS, 2020, 4 (03) : 278 - 293