sEMG-based torque estimation using time-delay ANN for control of an upper-limb rehabilitation robot | |
Chen Wang2,3; Liang Peng2; Zeng-Guang Hou1,2,3; Lincong Luo2,3; Sheng Chen2,3; Weiqun Wang2 | |
2018 | |
会议日期 | 2018-10-25 |
会议地点 | Shenzhen, China |
英文摘要 | Robotic-assisted rehabilitation of the upper limb following neurological injury can achieve best possible functional recovery when patients are engaged in the therapy. However, implementation of active training is still difficult as it’s challenging to detect human motion intention online and impose corresponding robot control. This paper introduces a novel upper-limb rehabilitation robot, and proposes a sEMGdriven (sEMG: surface Electromyography) torque estimation model based on artificial neural networks (ANN). The robot has three DOFs, of which the first two DOFs adopt a planar parallel structure, and the wrist module has an exoskeleton form. In this study, we design an impedance controller and an admittance controller for the first two DOFs and the wrist module, respectively. Specifically, for the first two DOFs, the assistance/resistance force at the end-effector was controlled according to its motions and desired interaction impedance; for the wrist module, an sEMG armband was used to collect 8 channels of sEMG signals from the forearm muscles, and a time-delay ANN model was developed to estimate the wrist pronation/supination torque, based on which the wrist rotation was controlled according to the human motion intention. To overcome the overfitting problem, besides the experimental samples of wrist rotation, both resting and co-contraction samples were collected for training. Finally, combining with the design of a virtual reality game and force fields, the proposed methods were implemented and tested experimentally on the upper-limb rehabilitation robot. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44879] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进机器人控制团队 |
通讯作者 | Zeng-Guang Hou |
作者单位 | 1.CAS Center for Excellence in Brain Science and Intelligence Technology 2.State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences 3.University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Chen Wang,Liang Peng,Zeng-Guang Hou,et al. sEMG-based torque estimation using time-delay ANN for control of an upper-limb rehabilitation robot[C]. 见:. Shenzhen, China. 2018-10-25. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论