基于脑机接口的家庭辅助机器人研究。
Study of the Home-Auxiliary Robot Based on BCI.
机构信息
School of Mechanic Engineering, Northeast Electric Power University, Jilin 132012, China.
College of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China.
出版信息
Sensors (Basel). 2018 Jun 1;18(6):1779. doi: 10.3390/s18061779.
A home-auxiliary robot platform is developed in the current study which could assist patients with physical disabilities and older persons with mobility impairments. The robot, mainly controlled by brain computer interface (BCI) technology, can not only perform actions in a person's field of vision, but also work outside the field of vision. The wavelet decomposition (WD) is used in this study to extract the δ (04 Hz) and θ (48 Hz) sub-bands of subjects' electroencephalogram (EEG) signals. The correlation between pairs of 14 EEG channels is determined with synchronization likelihood (SL), and the brain network structure is generated. Then, the motion characteristics are analyzed using the brain network parameters clustering coefficient (C) and global efficiency (G). Meanwhile, the eye movement characteristics in the F3 and F4 channels are identified. Finally, the motion characteristics identified by brain networks and eye movement characteristics can be used to control the home-auxiliary robot platform. The experimental result shows that the accuracy rate of left and right motion recognition using this method is more than 93%. Additionally, the similarity between that autonomous return path and the real path of the home-auxiliary robot reaches up to 0.89.
本研究开发了一种家用辅助机器人平台，旨在为身体残疾患者和行动不便的老年人提供帮助。该机器人主要通过脑机接口（BCI）技术进行控制，不仅能够在人的视野内执行动作，还能在视野外工作。本研究采用小波分解（WD）技术提取被试者脑电图（EEG）信号的δ（04 Hz）和θ（48 Hz）子带。通过同步似然（SL）确定 14 个 EEG 通道对之间的相关性，生成脑网络结构。然后，利用脑网络参数聚类系数（C）和全局效率（G）分析运动特征。同时，识别 F3 和 F4 通道中的眼动特征。最后，可以使用脑网络和眼动特征识别的运动特征来控制家用辅助机器人平台。实验结果表明，使用该方法进行左右运动识别的准确率超过 93%。此外，自主返回路径与家用辅助机器人的真实路径之间的相似度高达 0.89。
Zotero 插件