基于稳态视觉诱发电位的多自由度机械手实时控制系统

Research on Real-time Control System of Multi-DoF Manipulator Based on Steady State Visual Evoked Potential

将稳态视觉诱发电位作为多自由度机械手控制系统中一种新型、智能、实用的输入信号,设计了基于稳态视觉诱发电位的多自由度机械手控制系统,实现了脑电信号对机械手4个运动方向的实时控制。系统通过检测脑电信号中的稳态视觉诱发电位成分,通过离散平稳小波变换去除背景噪声,并利用短时傅里叶变换进行诱发电位的特征提取和识别,将其转换为外部机械手的控制命令。实验表明,控制系统的识别准确率达到75%以上。该系统的实现为延伸和提高人类对机器人的行为控制能力提供了一种新的方法。

A real-time control system of multi-DoF manipulator was presented with steady state visual evoked potential （SSVEP） as a novel, intelligent and useful input signal. In this system, the SSVEP-based electroencephalogram （EEG） was derived from scalp and then translated to four control commands of manipulator. In order to improve the performance of the system, the discrete smooth wavelet transform （SWT） and short-time Fourier transform （STFT） were used in signal processing. The experiment results show that the accuracy is above 75%. The realization of the system can provide a new way to enhance the human capability to control robot.