A brain-computer interface based semi-autonomous robotic system

Brain-computer interface (BCI) takes commands directly from the user's brain via electroencephalogram (EEG), which offers a solution for controlling the robotic system when users' hands are disabled or occupied. This paper describes a semi-autonomous robotic system that is able to execute grasping tasks based on BCI, thus offering an alternative control approach for robotic system. As BCI has limited information transfer rate and can easily cause fatigue in using, we utilize a stereo camera for object localization and convolutional neural network (you only look once version3, YOLOv3) for object identification to reduce the information needed from the brain in task execution, thus alleviating the workload for the user as well as increasing the efficiency of the system