A hybrid EEG-based BCI for robot grasp controlling

Abstract

Brain-Computer Interfaces (BCI) can help disable people to improve human — environment interaction and rehabilitation. Grasping objects with EEG-based BCI has become a popular and hard research in recent years due to the high degree of freedom robot and complex grasp planning. Unlike commonly used paradigms, we propose a pipeline of hybrid EEG-based BCI for robot grasping by shared control to solve the key problems including target object selection, robot intelligent planning and shared control by both user intension and robot. Six experimental users could successfully use the system to grasp a number of objects in a test scene. The results of grasping experiment demonstrate that our method achieve an effective performance.