脑控无人机
Mind-control drone
我使用自行组装搭建的16通道OpenBCI脑机接口装置和Tobii的眼球追踪器制作了一个脑控无人机的原型机。利用预先训练的机器学习Python脚本解析脑机接口收集到的脑电波连续时间序列数据,转换为方向控制信号传输给无人机控制系统以控制飞行方向。使用眼球追踪仪追踪视线在图传画面中的焦点,在特定区域触发镜头摆动信号传输给无人机控制系统以用视线焦点控制镜头方向。两套控制链路相结合,实现了不需要用手操作的脑控无人机原型。视频中使用了DJI大疆飞行模拟软件以便于演示。
I prototyped a mind-controlled drone using a self-assembled 16-channel OpenBCI brain-computer interface (BCI) device and a Tobii eye tracker. A pre-trained machine learning Python script was used to analyze the continuous time-series brainwave data collected by the BCI, converting it into directional control signals transmitted to the drone’s control system to control its flight direction. The eye tracker was used to track the focus of the gaze on the video feed, triggering a signal to move the camera when the gaze is directed at a specific area, which is then sent to the drone’s control system to control the camera's orientation with the gaze. The combination of these two control systems resulted in a brain-controlled drone prototype that does not require hand operation. The video demonstrates the prototype using DJI’s flight simulation software for easier visualization.
原型草图
Prototype sketch

原理草图
Mechanism sketch

控制系 统图示
Control system diagram
