基于视觉诱发电位脑机接口的四自由度机械手控制系统设计

摘要

Brain-computer interface (BCI) is a novel kind of human computer interface being explored since last decade. A 4-DOF robotic arm control system was designed based on visual evoked potential (VEP) brain-computer interface. In this real time system, electroencephalogram (EEG) was processed online and translated to nine control commands based on bayesian classifier to control the 4-DOF robotic arm. The experimental results demonstrate that the system is able to achieve an average information transfer rate of 20. 3 b/min with an average accuracy of 95%. The realization of the system can provide a new way to enhance the human capability to control robot.%脑机接口是近十年发展起来的一种新颖人机接口方式.设计了基于视觉诱发电位脑机接口四自由度机械手控制系统,该系统实现了脑电信号在线处理,通过贝叶斯分类器提取9个控制指令,完成对机械手4个自由度的实时控制.实验结果表明:该脑机接口控制系统平均传输速率为20.3 b/min,平均识别准确率达到95%.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.