Teleoperation control of a wheeled mobile robot based on Brain-machine Interface

Area of Science:

• Robotics
• Neuroscience
• Human-Computer Interaction

Background:

• Traditional mobile robot control methods lack intuitive interaction.
• Brain-Machine Interfaces (BMIs) offer a novel approach for controlling external devices.
• Electroencephalogram (EEG) provides a non-invasive method for capturing brain signals.

Purpose of the Study:

• To develop a novel teleoperation system for controlling a wheeled mobile robot (WMR) using EEG signals.
• To implement a Brain-Machine Interface (BMI) utilizing steady state visually evoked potentials (SSVEP) for EEG induction.
• To enable real-time trajectory adjustments and motion control of the WMR based on user's brain activity.

Main Methods:

• Utilized steady state visually evoked potentials (SSVEP) for non-invasive EEG signal induction via an online BMI system.
• Employed Canonical Correlation Analysis (CCA) classifier to recognize user's motion intention from EEG data.
• Integrated teleoperation techniques with Bezier curve path planning and an error model-based motion controller for real-time trajectory tracking.

Main Results:

• Successfully converted EEG classification results into motion commands for the WMR, including braking.
• Demonstrated real-time adjustment of robot trajectory based on EEG recognition.
• Achieved excellent trajectory tracking performance using velocity feedback control and an error model controller.

Conclusions:

• The proposed teleoperation system effectively controls a WMR using EEG-based BMI.
• The system demonstrates feasibility and high performance in brain-controlled robot navigation.
• This approach offers a promising direction for advanced human-robot interaction and teleoperation.