Quadcopter Flight Control Using a Non-invasive Multi-Modal Brain Computer Interface.

Area of Science:

• Neuroscience
• Robotics
• Human-Computer Interaction

Background:

• Brain-Computer Interfaces (BCIs) enhance life quality for individuals with disabilities by translating neural signals into device commands.
• Existing BCIs often face limitations in stability and accuracy for real-world applications.

Purpose of the Study:

• To develop and evaluate a multi-modal BCI system integrating motor imagery (MI) and steady-state visual evoked potentials (SSVEP).
• To achieve stable, accurate control of a quadcopter in three-dimensional space for practical tasks.

Main Methods:

• Combined MI and SSVEP signals using Complete Information Common Spatial Pattern (CICSP) and Canonical Correlation Analysis (CCA).
• Implemented eye-blinking for mode switching and utilized real-time global camera feedback.
• Conducted two physical flight tasks: a zig-zag pattern through a gate and an S-shaped route through two gates.

Main Results:

• The multi-modal BCI system demonstrated stable quadcopter control in physical flight tasks.
• Subjects achieved 86.5% accuracy in a complex flight task involving navigating through two gates.
• The system successfully translated neural signals into precise quadcopter movements.

Conclusions:

• The proposed multi-modal BCI significantly improves control accuracy and reduces task burden compared to single-modal systems.
• This approach offers enhanced performance for real-world BCI applications, particularly in controlling robotic systems.
• BCIs integrating MI and SSVEP show great potential for improving the quality of life for diverse user groups.