基于SSVEP直接脑控机器人方向和速度研究

直接用思维意图来控制机器人而没有大脑外周神经和肌肉的参与是人类的一个梦想，目前这一研究已成为国际前沿热点和突破点.传统的脑控机器人（Brain-controlled robot，BCR）主要控制其方向，而本文旨在探讨能够同时脑控机器人方向和速度的有效方法.采用可分类目标数多、单次识别率高且训练时间短的稳态视觉诱发电位（Steady state visual evoked potentials，SSVEP）脑机交互（Brain-computer/machine interaction，BCI/BMI）方法，为脑控机器人运动规划了向左、向右、前进和后退4个方向，设计了低速、中速和高速3级运动速度并组合了9个脑控指令；进而比较并优化了SSVEP刺激目标布局间距以及刺激目标闪烁时间，采用典型相关分析（Canonical correlation analysis，CCA）进行识别.结果表明恰当设置SSVEP刺激目标数及其布局间距和刺激目标闪烁时间，可以有效提高被试/用户直接脑控机器人的性能；优化的SSVEP刺激范式三结合适应SSVEP解码的典型相关分析，8名被试脑控机器人到达终点平均用时为2分40秒，最少用时1分29秒；同时，在脑控机器人运动过程中触碰障碍平均次数为0.88，最少碰触次数为0.本研究显示基于SSVEP的脑机交互可以作为直接脑控机器人灵活运动的一种可选方法，能够实现对机器人多个运动方向和多级速度的控制；也证实了适当增加刺激目标间距可以有效提高SSVEP-BCI脑控指令识别的正确率，说明了该脑控方法的性能与刺激被试的范式有关；再次验证了CCA算法在基于SSVEP的脑机交互中具有优良的效果.最后，为克服单一SSVEP范式存在的局限，本研究也尝试把该范式与运动想象相结合的混合范式用于脑控机器人方向和速度，并进行了初步的研究，表明可以进一步改善控制速度和提高被试舒适度.本文可望为基于SSVEP或与运动想象混合的脑机交互应用于分级或精细控制机器人方向和速度提供思路，并为直接脑控机器人技术推向实际应用打下一定的基础.

Direct-brain-controlled Robot Direction and Speed Based on SSVEP Brain Computer Interaction

Direct use of thinking to control a robot without peripheral nerves and muscles is a dream of human beings, and this research has become a hot spot and a breakthrough point in the world. The traditional brain-controlled robot (BCR) mainly controls the direction, and this paper aims to explore the effective method to control the direction and speed of robot through brain. Using the brain-computer/interaction (BCI/BMI) method based on steady state visual evoked potential (SSVEP), 9 instructions are designed to control the robot. And the canonical correlation analysis (CCA) method is used to identify EGG patterns. The results show that appropriate setting of the target number and its layout spacing and the flashing time can effectively improve the performance of the direct-brain-controlled robot. The optimization of the SSVEP stimulus paradigm three, the average time of 8 subjects controlled robot to reach destination using 2 minutes and 40 seconds, with a minimum of 1 minutes and 29 seconds. Meanwhile, the average number of touching obstacles is 0.88, the least touch number is 0, and the maximum number of touch is 3. This study shows that the BCI based on SSVEP can be used for the direct-brain-controlled robot. In order to overcome the limitations in the single SSVEP paradigm, this study also combines motor (Hybrid-BCI) imagery to control the robot. This paper is expected to provide ideas for the direction and speed control for the brain-computer interaction based on SSVEP or combined with motor imagery, and to provide a certain basis for practical direct-brain-controlled robot technology.