sEMG-based continuous motion estimation of upper limb using a novel noise-tolerant zeroing neurodynamic model combined with LSTM network

Continuous motion estimation of human limb plays a vital role in human-robot interaction (HRI) and collaboration (HRC), which can facilitate more natural and active HRI. However, the prediction accuracy of continuous motion estimation needs to be improved, moreover, the noise interference in motion estimation should be suppressed in practical applications. In this paper, the sEMG-based closed-loop model combining the noise-tolerant zeroing neural network (NTZNN) and the long short-term memory (LSTM) network (termed as the L-NTZNN closed-loop model) is proposed for continuous motion estimation in different noise-polluted conditions. On the basis of the LSTM model, the zeroing neural network-based (L-ZNN) and the gradient neural network-based (L-GNN) models are presented for comparison. The advantage of this work is that the L-NTZNN closed-loop model has higher prediction accuracy and stronger anti-noise performance in noise-polluted condition compared with the L-ZNN, the L-GNN, the LSTM and the Gaussian process regression (GPR) models. The root mean squared error (RMSE) and the coefficient of determination (R2) of the L-NTZNN in continuous motion estimation prove its superiority in different noise-polluted conditions (R2: 0.9881, 0.9812, 0.9858, 0.9775; RMSE: 0.0793, 0.1069, 0.0949, 0.1271). The Kruskal-Wallis test reports that the L-NTZNN closed-loop model has significantly ascendancy over the other models in respect of prediction accuracy and noise-tolerant property (p<0.05). In addition, the stability and generalization ability of the proposed L-NTZNN closed-loop model for different subjects are verified.