# Research on Upper Limb Motion Intention Classification and Rehabilitation Robot Control Based on sEMG

## TL;DR

This paper explores using sEMG signals to classify upper limb movements and control a rehabilitation robot, aiming to improve recovery through accurate motion intention recognition.

## Contribution

The study introduces a multi-stream convolutional neural network for nine-class sEMG classification and applies it to control a rehabilitation robot.

## Key findings

- A musculoskeletal model of the upper limb was validated using OpenSim simulations.
- The MLCNN model achieved high classification accuracy for nine upper limb motion intentions.
- The rehabilitation robot controlled by sEMG showed smooth and accurate motion across different trajectories.

## Abstract

sEMG is a non-invasive biomedical engineering technique that can detect and record electrical signals generated by muscles, reflecting both motor intentions and the degree of muscle contraction. This study aims to classify and recognize nine types of upper limb motor intentions based on surface electromyography (sEMG) and apply them to the interactive control of an end-effector rehabilitation robot. The research begins with selecting muscles and data preprocessing, incorporating the generation mechanism of sEMG along with the anatomical and kinesiological principles of upper limb muscles. Next, a musculoskeletal model of the upper limb is established and validated through simulations in OpenSim. To avoid the drawbacks of modeling methods, traditional machine learning and deep learning methods are employed to perform a nine-class classification task on the sEMG data, comparing the classification accuracy of different approaches. Finally, the motor intentions extracted using a multi-stream convolutional neural network (MLCNN) are utilized to control the iReMo® end-effector rehabilitation robot, with the system’s motion smoothness and accuracy evaluated through tests involving different trajectories.