Dynamic gripping force estimation and reconstruction in EMG-based human-machine interaction

Electromyography (EMG) can reveal the state of muscle activity in advance, therefore, it has been widely used in human-machine interaction (HMI) to predict human intention. Force estimation from EMG signals is acknowledged as an important research topic in HMI. In order to develop a simple and smooth HMI system, it is necessary to estimate the dynamic force effectively and smoothly from a small number of EMG electrodes. In this paper, we have proposed an EMG-based dynamic force reconstruction scheme applied in HMI system. A deep neural prediction network using one-dimensional convolutional structure has been proposed to learn the com-plex EMG features automatically from three-channel EMG signals. This model was applied in our interactive system to estimate dynamic force and reconstruct it on a robotic gripper for precise EMG-based robot control. Our proposed model outperformed the two-dimensional convolutional neural network (CNN) method and feature-based linear regression. And it can meet the requirement of online interaction. The offline and online tests have shown good estimation performance with R2 of 0.99 and 0.83, respectively. The average prediction speed has reached 115.5 mu s per sample. The system has avoided tedious feature extraction process and has demonstrated dynamic recognition in real time which can further advance various prosthesis and assistive ro-botic applications in the future.