Noninvasive Brain-computer Interface Based High-level Control of a Robotic Arm for Pick and Place Tasks

Abstract

Recent advances in brain-computer interfaces (BCIs)and robotic arms have allowed us to operate robotic arms through BCIs. However, the majority of the previous studies adopted low-level control strategy, which could be time-consuming and tedious. Therefore, this study attempted to design a new high-level control strategy, where users selected the target location using the proposed steady-state visual evoked potential (SSVEP)-based BCI, and the robotic arm automatically transported objects to the destination. Online results indicated that a command for the proposed BCI controlled robotic arm system could be selected from 25 possible choices in 1.75 s visual stimulation with 95.50% accuracy. These results demonstrated that the proposed SSVEP-based BCI controlled robotic arm system had high precision. This study showed that the proposed BCI controlled robotic arm has the potential for successfully assisting individuals with upper limb disabilities to independently manipulate and transport objects.