论文:2017,Vol:35,Issue(1):116-120
引用本文:
谢松云, 段绪, 冯怀北, 孟雅, 陈刚. 基于意识任务的机器人脑控系统[J]. 西北工业大学学报
Xie Songyun, Duan Xu, Feng Huaibei, Meng Ya, Chen Gang. Robot Control System Using a Mental Task-Based Brain Computer Interface[J]. Northwestern polytechnical university

基于意识任务的机器人脑控系统
谢松云, 段绪, 冯怀北, 孟雅, 陈刚
西北工业大学 电子信息学院, 陕西 西安 710072
摘要:
目前机器人的控制系统基本需要双手遥控,对残疾人等无法提供便利,提出了一种全新的脑电信号(electroencephalography,EEG)控制机器人方法。采用无需外界刺激的意识任务诱发特征EEG,通过便携式脑电设备采集EEG,经过特征提取与指令分类,实现对机器人的控制。针对意识任务需要被试进行大量的训练,设计了离线训练系统。针对EEG信噪比较低的问题,研究了意识任务下EEG处理方法。最后设计了在线机器人脑控系统,利用想象左手运动、想象右手运动、想象单词生成分别控制机器人左转、右转与前进,利用眨眼信号控制机器人停止。实验结果表明,从准确率、舒适度两方面来看,基于意识任务的机器人脑控系统有效实现了机器人的控制。
关键词:    脑控系统    机器人控制    EmotivEpoc    意识任务    LTCFB-CSP算法   
Robot Control System Using a Mental Task-Based Brain Computer Interface
Xie Songyun, Duan Xu, Feng Huaibei, Meng Ya, Chen Gang
School of Electronics and Information, Northwestern Polytechnical University, Xi'an 710072, China
Abstract:
The existing robot control system basically needs hand remote control, and could not provide facilities for people with disabilities. A new EEG control robot method is proposed. In this paper, EEG is induced by mental task without external stimuli and collected by portable EEG cap. After feature extraction and classification, the robot is controlled. Long time training is needed for mental task, and the off-line training system is designed. Aimed at the low SNR of EEG, the process method of EEG with specific pattern is studied. Finally, an online robot control system is designed, subjects can control the robot turning left, turning right, going straight and going back using left-hand motor imagery, right-hand motor imagery, word generation task and blink, respectively. The experimental result shows that from the perspective of accuracy and comfort, the robot-based brain-control system based on mental task can efficiently control the robot.
Key words:    robot control    brain computer interface    EEG    portable device    data acquisition    EmotivEpoc    artificial removal    feature extraction    pattern recognition    mental task    motor imagery    eye blink    MATLAB    common spatial pattern    local temporal correlation    filter bank    support vector machines    ERD/ERS    topological graph    power spectrum   
收稿日期: 2016-09-18     修回日期:
DOI:
基金项目: 国家自然科学基金(61273250)、西北工业大学研究生创业种子基金(Z2016124)以及大学生创新创业训练计划项目(201510699145)资助
通讯作者:     Email:
作者简介: 谢松云(1968-),女,西北工业大学教授、博士生导师,主要从事神经信息处理、脑认知与脑机接口及动态目标识别与跟踪的研究。
相关功能
PDF(2858KB) Free
打印本文
把本文推荐给朋友
作者相关文章
谢松云  在本刊中的所有文章
段绪  在本刊中的所有文章
冯怀北  在本刊中的所有文章
孟雅  在本刊中的所有文章
陈刚  在本刊中的所有文章

参考文献:
[1] Wolpaw J, Wolpaw E W. Brain-Computer Interfaces:Principles and Practice[M]. New York, Oxtord University Press, 2012
[2] McFarland D J, Miner L A, Vaughan T M, et al. Mu and Beta Rhythm Topographies During Motor Imagery and Actual Movements[J]. Brain Topography, 2000,12(3):177-186
[3] Martinez-Leon J, Cano-Izquierdo J, Ibarrola J. Are Low Cost Brain Computer Interface Headsets Ready for Motor Imagery Applications?[J]. Expert Systems with Applications, 2016,49:136-144
[4] 谢松云, 王立楠, 张斌,等. 用于飞行员状态监控的视觉空间选择性注意研究[J]. 西北工业大学学报, 2014, 32(2):268-272 Xie Songyu, Wang Linan, Zhang Bin, et al. On Spoutial Selective Atlention Pattern and Its Application to Monitoring of Polins Brain Fuction State[J]. Journal of Northwestern Polytechnical University, 2014, 32(2):268-272(in Chinese)
[5] Ang K K, Chin Z Y, Wang C, et al. Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b[J]. Frontiers in Neuroscience, 2012(6):39-47
[6] Zhang R, Xu P, Liu T, et al. Local Temporal Correlation Common Spatial Patterns for Single Trial EEG Classification during Motor Imagery[J]. Computational and Mathematical Methods in Medicine, 2013, 2013(3):1-7