Lower limb movement intention recognition for rehabilitation robot aided with projected recurrent neural network

Abstract

For the lower limb rehabilitation robot, how to better realize intention recognition is the key issue in the practical application. Recognition of the patient’s movement intention is a challenging research work, which needs to be studied from the shallow to the deep. Specifically, it is necessary to ensure that the movement intention of the normal person can be accurately recognized, and then improve the model to realize the recognition of the movement intention of the patients. Therefore, before studying the patient’s movement intention, it is essential to consider the normal person first, which is also for safety considerations. In recent years, a new Hill-based muscle model has been demonstrated to be capable of directly estimating the joint angle intention in an open-loop form. On this basis, by introducing a recurrent neural network (RNN), the whole prediction process can achieve more accuracy in a closed-loop form. However, for the traditional RNN algorithms, the activation function must be convex, which brings some limitations to the solution of practical problems. Especially, when the convergence speed of the traditional RNN model is limited in the practical applications, as the error continues to decrease, the convergence performance of the traditional RNN model will be greatly affected. To this end, a projected recurrent neural network (PRNN) model is proposed, which relaxes the condition of the convex function and can be used in the saturation constraint case. In addition, the corresponding theoretical proof is given, and the PRNN method with saturation constraint has been successfully applied in the experiment of intention recognition of lower limb movement compared with the traditional RNN model.

Extraction and Analysis of Foot Bone Shape Features Based on Deep Learning

“…In order to improve the utilization of motion capture data, in recent years, human motion data prediction, motion sequence fragment transition, and other technologies emerged. The main prediction methods of human movement data include deep learning models based on adversarial neural network and recurrent neural network as well as traditional methods [ 18 ]. The transition technology models of motion sequence fragments mainly include probability statistics, motion graph, and deep learning.…”

A Framework and Algorithm for Human-Robot Collaboration Based on Multimodal Reinforcement Learning

“…[ 16 ] designed a new approach for intention understanding of upper limb movements using mobile electroencephalography (EEG) via LSTM-RNN, which could provide early warning of impending danger to improve the safety of the system. Reference [ 17 ] constructed a projective recurrent neural network to estimate the joint angular intention of the user during motion using a Hill-based muscle model. Another interesting approach exploits the human's preference to adapt the robot's behavior based on the human's feedback.…”

Design and Implementation of Bionic Flying Fish with Applications

“…For the target tracking problem, the input of the k -WTA model can be transformed as follows [26][27][28]:…”