An EEG-/EOG-Based Hybrid Brain-Computer Interface: Application on Controlling an Integrated Wheelchair Robotic Arm...

Area of Science:

• Neuroscience
• Robotics
• Rehabilitation Engineering

Background:

• Existing brain-computer interfaces (BCIs) typically control single assistive devices.
• Complex daily tasks often require integrated control of multiple robotic systems, posing significant challenges for accuracy and reliability.
• There is a need for advanced BCIs capable of managing multi-device robotic systems.

Purpose of the Study:

• To propose and evaluate a novel hybrid BCI (hBCI) for high-accuracy control of an integrated wheelchair-robotic arm system.
• To assess the feasibility of using combined electroencephalogram (EEG) and electrooculogram (EOG) signals for complex assistive control.
• To demonstrate the potential of the hBCI in enabling users to perform intricate daily activities.

Main Methods:

• Developed a hybrid BCI system integrating EEG and EOG signals.
• Utilized motor imagery (MI) of hand movements for wheelchair navigation (left/right turns).
• Incorporated eye blinks and eyebrow raising movements for additional wheelchair and robotic arm commands.
• Designed a mobile self-drinking experiment with high accuracy requirements for evaluation.

Main Results:

• The proposed hBCI achieved satisfactory control accuracy for the integrated wheelchair-robotic arm system.
• Subjects were able to perform complex actions using the multi-device system.
• The system demonstrated robust performance in a challenging self-drinking experiment.

Conclusions:

• The novel hBCI effectively controls integrated robotic systems with high accuracy.
• This technology shows significant potential for application in complex daily tasks for individuals requiring assistive devices.
• The findings pave the way for more sophisticated and integrated BCI-controlled assistive solutions.