A Flexible Meal Aid Robotic Arm System Based on SSVEP

As a significant part of Human-Computer Interaction (HCI), Brain-Computer Interface (BCI) is paid more and more attention because its capability of exchanging information without any movement but through the mind. This technology can improve the control of people with the outside world, especially the disabled. In the scene of self-feeding, the effect is particularly evident. This paper proposes a flexible Steady-State Visual Evoked Potential (SSVEP) based method of controlling a robotic arm to help users with motor impairments to have some solid food. The user can control the robotic arm to grasp solid food by looking at the visual stimulus interface. The functions of visual stimulus targets are elaborated designed to make the operation convenient and flexible. The specific stimulus frequency is extracted by Canonical Correlation Analysis (CCA). Experiments are carried out in eight subjects and the results indicate the accuracy and effectiveness of the proposed system.