Related Experiment Video
Updated: Jun 25, 2026
11:18
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
Published on: March 2, 2015
A self-paced brain-computer interface for controlling a robot simulator: an online event labelling paradigm and an
Chun Sing Louis Tsui1, John Q Gan, Stephen J Roberts
1School of Computer Science and Electronic Engineering, University of Essex, Colchester, CO4 3SQ, UK. csltsu@essex.ac.uk
Medical & Biological Engineering & Computing
|February 20, 2009
Summary
This study introduces a new self-paced brain-computer interface (BCI) system for controlling robots. The novel paradigm effectively enables online training and adaptation for motor imagery BCIs, overcoming previous challenges.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Human-Computer Interaction
Background:
- Non-stationarity in electroencephalography (EEG) signals necessitates online adaptation in brain-computer interface (BCI) systems.
- Self-paced BCIs offer natural interaction but pose challenges for online training due to unknown user intention and timing.
Purpose of the Study:
- To propose a novel motor imagery-based self-paced BCI paradigm.
- To create a controlled environment for investigating online training and adaptation of self-paced BCIs.
- To enable effective online adaptation by providing user's control intention and timing.
Main Methods:
- Development of a novel self-paced BCI paradigm using motor imagery.
- Implementation of a specifically designed environment to capture user intention and timing.
- Utilizing an extended Kalman filter for adaptive BCI classifier parameter tuning.
Main Results:
- Demonstrated the effectiveness of the proposed paradigm for online self-paced BCI training.
- Successfully adapted BCI classifier parameters using the extended Kalman filter.
- Collected experimental data from four subjects on online self-paced BCI training.
Conclusions:
- The proposed paradigm effectively facilitates online training and adaptation for motor imagery-based self-paced BCIs.
- The developed environment provides crucial data for investigating online BCI adaptation.
- The study validates the approach with experimental results from multiple subjects.
