A robotic arm control system with simultaneous and sequential modes combining eye-tracking with steady-state visual...

Area of Science:

• Neuroscience
• Robotics
• Human-Computer Interaction

Background:

• Single-modal brain-computer interfaces (BCIs) exhibit limitations in flexibility, autonomy, and subject fatigue.
• Existing BCIs often require extensive calibration and lack user control over system operation.

Purpose of the Study:

• To develop an asynchronous robotic arm control system integrating steady-state visual evoked potentials (SSVEP) and eye-tracking within a virtual reality (VR) environment.
• To offer both simultaneous and sequential control modes, enhancing user autonomy and reducing visual fatigue.

Main Methods:

• Developed a hybrid BCI (h-BCI) system combining electroencephalography (EEG) and eye-gaze tracking.
• Implemented simultaneous mode with decision-level fusion and an adjustable stimulus window.
• Introduced sequential mode with gaze-based target selection and EEG-based classification, allowing for user-initiated command rejection.

Main Results:

• Offline experiments demonstrated high accuracy (90.50% simultaneous, 90.47% sequential) and information transfer rates (60.02 bits/min simultaneous, 45.38 bits/min sequential).
• Online experiments showed successful robotic arm grasping tasks in both modes.
• Subjects reported increased autonomy, reduced visual fatigue, and a preference for the sequential mode.

Conclusions:

• The proposed h-BCI system effectively overcomes limitations of single-modal BCIs.
• The system offers enhanced autonomy, reduced user fatigue, and improved efficiency for robotic arm control.
• The hybrid approach caters to individual needs and demonstrates practical applicability in VR environments.