Related Experiment Video
Updated: Jul 3, 2025
09:42
Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients
Published on: September 1, 2023
1.3K
How Integration of a Brain-Machine Interface and Obstacle Detection System Can Improve Wheelchair Control via
Tomasz Kocejko1, Nikodem Matuszkiewicz1, Piotr Durawa1
1Department of Biomedical Engineering, Faculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology, Narutowicza 11/12, 80-233 Gdansk, Poland.
Sensors (Basel, Switzerland)
|February 10, 2024
Summary
This study developed a brain-machine interface (BMI) using EEG signals and CNNs for robot control. The system integrates obstacle detection, offering a potential solution for individuals with mobility challenges.
Area of Science:
- Neuroscience
- Robotics
- Human-Computer Interaction
Background:
- Conventional vehicle operation presents challenges for individuals with mobility impairments.
- Brain-machine interfaces (BMIs) offer alternative control methods by interpreting neural signals.
- Integrating obstacle detection enhances the safety and usability of BMI-controlled systems.
Purpose of the Study:
- To develop and evaluate a BMI system for controlling a wheeled robot using movement imagery.
- To implement an integrated obstacle detection system for collision avoidance.
- To assess the feasibility of using surface electroencephalography (EEG) for real-time robotic control.
Main Methods:
- Utilized a modified 10-20-electrode setup for electroencephalography (EEG) signal acquisition.
- Designed and trained two Convolutional Neural Network (CNN) models for classifying motor imagery and relaxation states from EEG data.
- Integrated a computer vision-based obstacle detection system with the BMI for real-time robotic navigation.
Main Results:
- Achieved 83% accuracy in classifying EEG signals related to mental activity.
- Successfully controlled a mobile robot in real-time using classified EEG signals.
- Demonstrated the feasibility of integrating obstacle detection for collision avoidance in BMI-controlled vehicles.
Conclusions:
- The developed BMI system effectively translates motor imagery into robot control.
- The integration of EEG-based control and computer vision-based obstacle detection is feasible for safe vehicle operation.
- This technology holds promise for assisting individuals with paralysis in controlling wheelchairs and other vehicles.
