A Human-Machine Interface Based on an EOG and a Gyroscope for Humanoid Robot Control and Its Application to Home...

Area of Science:

• Robotics
• Human-Computer Interaction
• Assistive Technology

Background:

• Human-machine interfaces (HMIs) are crucial for robot teleoperation, especially for individuals with motor disabilities.
• Existing HMIs face challenges in generating rapid, accurate, and sufficient control commands.
• Enhancing physical environment interaction for users with motor impairments is a key goal.

Purpose of the Study:

• To propose an asynchronous HMI using electrooculogram (EOG) and gyroscope for robot control.
• To enable users to control robotic systems via self-paced features like double blinks and head rotations.
• To improve the accuracy and reduce the response time of control commands for robot teleoperation.

Main Methods:

• Developed an asynchronous HMI integrating EOG and gyroscope sensors.
• Utilized double blink and head rotation as endogenous control features within a multilevel graphical user interface (GUI).
• Implemented a continuous control strategy using 'motion start' and 'motion stop' commands for robot actions.

Main Results:

• Achieved high accuracy (99.2%) and low response time (2.34s) in a trigger task with 20 options.
• Demonstrated effective humanoid robot control in a home service experiment, including object manipulation.
• Showcased improved performance with a time ratio of 1.22 and command ratio of 1.18 compared to manual control.

Conclusions:

• The proposed EOG and gyroscope-based HMI effectively provides sufficient commands with high accuracy and low response time.
• The continuous control strategy enhances humanoid robot operation, simplifying complex tasks.
• This HMI system shows significant potential for improving robot teleoperation and empowering users with motor disabilities.