Related Experiment Video
Updated: Jun 14, 2025
10:51
An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
Published on: March 10, 2011
13.7K
Bio-inspired EEG signal computing using machine learning and fuzzy theory for decision making in future-oriented
Haewon Byeon1, Aadam Quraishi2, Mohammed I Khalaf3
1Department of AI and Software, Inje University, Gimhae 50834, Republic of Korea; Inje University Medical Big Data Research Center, Gimhae 50834, Republic of Korea.
SLAS Technology
|August 29, 2024
Summary
This study introduces Fuzzy Brain-Control Fusion Control to improve brain-controlled vehicle performance. The new method enhances control accuracy by combining driver intent with automated decisions for better autonomous driving.
Area of Science:
- Robotics and Artificial Intelligence
- Neuroscience and Human-Computer Interaction
Background:
- Brain-Controlled Vehicles (BCVs) rely on Brain-Computer Interfaces (BCIs) for driver input via electroencephalogram (EEG) signals.
- Current BCIs face limitations in accuracy, command recognition, and execution speed, leading to suboptimal BCV control.
- Improving BCV control performance while maintaining BCI accuracy is a significant challenge.
Purpose of the Study:
- To introduce a novel fuzzy logic-based technique, Fuzzy Brain-Control Fusion Control, to enhance the control capabilities of BCVs.
- To address the limitations of existing BCI systems in autonomous vehicle applications.
- To develop a system that fuses driver intent with automated control for more robust and human-aligned vehicle operation.
Main Methods:
- Utilized Fuzzy Discrete Event System (FDES) supervisory theory to validate the accuracy of driver's brain-controlled commands.
- Developed a fuzzy logic-based automatic controller for real-time decision-making based on vehicle state.
- Implemented a secondary fuzzy reasoning layer to fuse driver commands and automated decisions for final output.
Main Results:
- Demonstrated the viability of the proposed Fuzzy Brain-Control Fusion Control technique using a Consistent State Visual Evoked Potential (SSVEP) BCI.
- The fusion approach aims to create more accurate and human-intent-aligned adjustments in BCV operation.
- The system shows potential for improving the control execution of BCI-powered vehicles.
Conclusions:
- The Fuzzy Brain-Control Fusion Control method offers a promising approach to overcome current BCV performance limitations.
- Further research is recommended to validate and optimize the system for enhanced control execution in BCI-fueled cars.
- The technique holds potential for advancing autonomous driving technology through improved human-machine integration.
