深度学习技术在EMG机械手臂的手势控制系统设计中的应用
摘 要：肌肉电信号（以下简称EMG）是肌肉收缩伴随的电信号，利用计算机可以将EMG进行信号编码，实现机械手臂等控制。通常来讲EMG传感器难以捕获手指手腕动作的微弱电位变化，因此传统的EMG机械手臂在工程设计过程中可能会遇到控制不精确、交互效果差等问题。文章探讨深度学习技术在EMG机械手臂的手势控制系统设计中的应用，同时为EMG的相关设计研究提供一定的参考价值。
关键词：深度学习；EMG；机械手臂；手势控制系统设计；应用
中图分类号：TP391 文献标识码：A
文章编码：1672-7053(2020)08-0028-02
Abstract：EMG is the electrical signal that accompanies muscle contraction. It can be coded by the computer to achieve control of the robotic arm. Generally speaking, EMG sensor is difficult to capture the weak potentials changes from finger and wrist action. Therefore, traditional EMG robotic arm may encounter problems such as inaccurate control and useless interaction effect in the engineering design process. This paper discusses and analyzes the advantages of artificial intelligence technology in EMG signal processing and designs a set of gesture motions.This paper discusses the application of deep learning technology in the design of gesture control system of EMG robotic arm, in order to provide some reference value for the design and research of EMG.
Key Words：Deep learning; EMG. Robotic arm; Design of gesture control system; Application
