Towards Utilization of Error-Related Potentials for Brain-to-Vehicle Communication
Embedded Files
A broad scope of a graphical environment from an omniscient viewpoint. A vehicle at its A) initial position on a T-shaped maze in the cued experiment. B) starting point on a track in the control experiment.
Abstract
Brain-computer interfaces (BCIs) rely on accurate classification of a user’s intent in order to perform the correct actions. However, when used in reality, devices controlled by BCIs may often react differently from what the user intended due to noise and other factors resulting in misclassification. In such cases, error-related potentials (ErrPs) may be evoked and can be captured from the user’s neural signals. Detection of these ErrPs can then be used to recognize and correct erroneous responses. In this research, we have created a graphical application in which the user drives a virtual car from a first-person perspective. Results of our experiments show that ErrPs can be captured from the user when the car moves differently from how the user intended to drive.
Contribution: I designed cued experiment and Unity-based simulator (used for both cued experiment and control experiment). I participated in both cued experiment and control experiment as a subject. I analyzed experimental results for cued experiment and wrote related parts for the below paper.
Publication
Jin Woo Choi, Taehyean Choi, Shinjeong Kim, and Sungho Jo. Towards Utilization of Error-Related Potentials for Brain-to-Vehicle Communication. In 2019 7th International Winter Conference on Brain-Computer Interface (BCI), pages 1-6. IEEE, 2019. [pdf]
Experiments
The timeline of experimental paradigm in the cued experiment. A single vehicular rotation consists of an initialization of the vehicle’s position, forward movement of the vehicle, left or right arrow cue indication, cross appearance for subject’s attention, and a correct or erroneous vehicle rotation. The vehicle maintained its forward movement until its rotation.
The timeline of experimental paradigm in the control experiment. A single vehicle movement selection consists of a choice availability notation (cross), and a EEG signal recording notation (cross vanished) along with the movement change on the vehicle. When the movement of the vehicle changed, it maintained the movement until next command was given.
Results
EEG signals from the electrode position FCz in the cued experiment and the control experiment. A) The upper figure indicates EEG signals from each subject when the vehicle moved differently from the arrow cue. The lower figure indicates EEG signals from each subject when the vehicle moved correctly as the direction of the cue. B) The upper figure indicates EEG signals from each subject when the vehicle moved differently from the user’s command. The lower figure indicates EEG signals in which the vehicle moved correctly as the user’s command
Classification accuracy for cued experiment
Classification accuracy for control experiment
Page updated
Google Sites
Report abuse