moabb.datasets.BNCI2016_002#

class moabb.datasets.BNCI2016_002[source]#

BNCI 2016-002 Emergency Braking during Simulated Driving dataset.

Dataset summary

#Subj

15

#Chan

69

#Trials / class

varies brake / EMG

Trials length

1.5 s

Freq

200 Hz

#Sessions

1

Participants

  • Population: healthy

  • Age: 30.6 years

  • Handedness: right-handed

  • BCI experience: naive

Equipment

  • Amplifier: BrainAmp

  • Electrodes: Ag/AgCl

  • Montage: 10-20

  • Reference: Car

Preprocessing

  • Data state: preprocessed

  • Steps: lowpass filtering, bandpass filtering, notch filtering, rectification, downsampling/upsampling, baseline correction

  • Re-reference: car

Data Access

  • DOI: 10.1088/1741-2560/8/5/056001

Experimental Protocol

  • Paradigm: p300

  • Feedback: visual (colored circle indicating distance: green <20m, yellow otherwise; brakelight flashing)

  • Stimulus: oddball

Dataset summary

Name

#Subj

#Chan

#Trials/class

Trials length

Sampling Rate

#Sessions

BNCI2016_002

15

69

~200 brake events

1.0s

200Hz

1

Dataset from [1].

Dataset Description

This dataset contains EEG and physiological signals recorded during emergency braking maneuvers in a driving simulator. The study demonstrated that drivers’ intentions to perform emergency braking can be detected from brain and muscle activity prior to the behavioral response, enabling predictive braking assistance systems.

Participants drove in a realistic driving simulator, maintaining distance from a lead vehicle while navigating curves and traffic. When the lead vehicle unexpectedly braked (emergency situation), subjects had to brake as quickly as possible. The dataset captures the neural and physiological signatures preceding emergency braking actions.

Participants

  • 18 subjects (14 males, 4 females) - currently 15 subjects available

  • Age: 30.6 +/- 5.4 years

  • All healthy with valid driver’s licenses

  • Location: Berlin Institute of Technology (TU Berlin), Germany

Recording Details

  • Equipment: BrainProducts actiCap system with BrainAmp amplifiers

  • Channels: 59 EEG + 2 EOG + 1 EMG + 7 driving-related signals = 69 total

  • Sampling rate: 200 Hz (downsampled from 1000 Hz)

  • Reference: Common average reference

  • EEG electrode montage: Extended 10-20 system

Additional Channels

  • EOGv, EOGh: Vertical and horizontal electrooculogram

  • EMGf: Electromyogram (right foot, tibialis anterior muscle)

  • lead_gas, lead_brake: Lead vehicle gas/brake pedal positions

  • dist_to_lead: Distance to lead vehicle

  • wheel_X, wheel_Y: Steering wheel position

  • gas, brake: Subject’s gas/brake pedal positions

Experimental Procedure

  • Three 45-minute driving blocks per subject (135 minutes total)

  • Driving task: Follow a lead vehicle, maintain safe distance

  • Emergency situations: Lead vehicle brakes unexpectedly

  • Subject response: Emergency braking required

  • Inter-trial interval: Variable (realistic driving conditions)

Event Codes

For P300 paradigm compatibility, events are mapped to Target/NonTarget:

  • Target: Lead car starts braking (emergency situation onset, originally car_brake)

  • NonTarget: Lead car driving normally (originally car_normal)

Additional events (not used for P300 classification):

  • car_hold: Lead car holding/stopped

  • car_collision: Collision occurred (subject failed to brake in time)

  • react_emg: Subject’s EMG reaction detected (braking initiated)

Key Findings

The study found that combining EEG and EMG signals enables detection of emergency braking intention 130 ms earlier than pedal-based systems alone. At 100 km/h, this corresponds to a 3.66 m reduction in braking distance.

The EEG analysis revealed a characteristic event-related potential signature comprising three components:

  1. Sensory registration of critical traffic situations

  2. Mental evaluation of the sensory information

  3. Motor preparation

References

[1]

Haufe, S., Treder, M. S., Gugler, M. F., Sagebaum, M., Curio, G., & Blankertz, B. (2011). EEG potentials predict upcoming emergency brakings during simulated driving. Journal of Neural Engineering, 8(5), 056001. https://doi.org/10.1088/1741-2560/8/5/056001

Notes

Added in version 1.3.0.

This dataset is valuable for research on:

  • Predictive braking assistance systems

  • Neuroergonomics and driving safety

  • Real-time detection of emergency intentions

  • Multimodal biosignal integration (EEG + EMG + vehicle dynamics)

The paradigm represents a unique blend of ERP (event-related potential) analysis with ecological validity in a naturalistic driving context.

Data Availability: Currently 15 of 18 subjects are available. Files are hosted at the BBCI (Berlin Brain-Computer Interface) archive.

License: Creative Commons Attribution Non-Commercial No Derivatives (CC BY-NC-ND 4.0)

On this page