Estimating Simultaneous and Proportional Finger Force Intention Based on sEMG Using a Constrained Autoencoder

Abstract

To boost the usability of a robotic prosthetic hand, providing degrees of freedom to every single finger is inevitable. Under the name of simultaneous proportional control (SPC), many studies have proposed methods to achieve this goal. In this paper, we propose a method to generate a regression model of a neuromuscular system called the Constrained AutoEncoder Network (CAEN) that estimates finger forces using a surface electromyogram (sEMG). Modifying the autoencoder from deep learning, the model is generated in a semi-unsupervised manner where only sEMG data and finger labels are used. In the learning process, the finger labels are used at the central layer of the network, where the three finger forces are estimated, to prevent penetration of other finger signals to each finger node and the network is trained in the constrained manner. This process results in independence among estimated finger forces such that the manipulability of multiple fingers is highly improved. The proposed model was compared with four previously reported SPC models in two tests: offline and online tests. In the offline test, the CAEN showed good results but not the best results. However, in the online test, which involved reaching target positions for three fingers simultaneously and proportionally, the proposed model showed the best results for three of six online performance indices (the completion rate, completion time, and throughput). Emphasizing the independence among estimated finger forces in the training process is the key point of the proposed method distinct from previous studies and the results showed that it was effective in the online control.INDEX TERMS Autoencoder, finger intention estimation, neural network, surface electromyogram (sEMG).

Real-Time Finger Force Estimation Robust to a Perturbation of Electrode Placement for Prosthetic Hand Control

“…In a previous study, CAEN was able to estimate the simultaneous movement of fingers with high accuracy based on sEMG signals, and the approach improved the real-time control performance by ensuring independence between fingers. The CAEN described in reference [10] consists of input layer (U ), 1st hidden layer (encoding layer, E), finger intention layer ( F), 3rd hidden layer (decoding layer, D), and output layer (U ). the calculation process of the CAEN is as follows.…”

“…This model showed high performance in estimating wrist force intention, and the authors emphasized the need for a nonlinear model. We proposed a new semi-unsupervised ANN that borrows only the structure of the autoencoder in a manner named the constrained autoencoder (CAEN) [10]. A learning method that maximizes the independence between fingers was proposed, and clinical tests showed high estimation accuracy in estimating finger force intention.…”