Continuous shared control of a mobile robot with brain-computer interface and autonomous navigation for daily...

Area of Science:

• Neuroscience
• Robotics
• Human-Computer Interaction

Background:

• Electroencephalography (EEG) based brain-computer interfaces (BCI) show promise for rehabilitation and assistance.
• Achieving continuous control of brain-actuated mobile robots remains a significant challenge.

Purpose of the Study:

• To propose and validate a continuous shared control strategy for mobile robot systems.
• To integrate continuous BCI control with autonomous navigation for enhanced robot operation.
• To dynamically adjust the balance between BCI input and autonomous navigation based on user performance.

Main Methods:

• Developed a continuous shared control strategy combining continuous BCI and autonomous navigation.
• Utilized visual-based simultaneous localization and mapping (SLAM) for environmental mapping.
• Implemented a brain-based shared control dynamic window approach (BSC-DWA) for trajectory evaluation.
• Conducted two-stage training and online shared control experiments with human subjects.

Main Results:

• Naïve subjects achieved high continuous control performance, with an average percent valid correct rate of approximately 97% and total correct rate over 80% during training.
• All participating subjects successfully completed navigation tasks in an unknown corridor using the continuous shared control system.
• The system demonstrated feasibility and effectiveness in integrating continuous BCI, shared control, autonomous navigation, and visual SLAM.

Conclusions:

• The proposed continuous shared control framework is feasible and effective for BCI-driven mobile robot navigation.
• This approach shows significant potential for brain-driven assistive mobile robots and wheelchairs in daily applications.
• The dynamic fusion of BCI and autonomous navigation enhances control capabilities for complex tasks.