Introduction

The HRI Driver Behavior Dataset (HDBD) contains driver behavior collected using simulator and real scene videos. The dataset contains videos of vehicle and driver (participant) behavioral and physiology data.

• Signals collected from 28 participants 
  • Behavioral – gaze position and takeover intention 
  • Physiology - heart rate (HR), galvanic skin response (GSR) 
• Environmental (weather, HMI, traffic conditions) and vehicle sensory information (speed, brake) corresponding to the videos
• Sensors
  • Tobii nano Pro (eye gaze related information)
  • Shimmer3
  • Vehicle/driving simulator sensory data from CAN-bus

Video

Downloads

This dataset corresponds to the paper, " Gaze Behavior Using Joint Embedding With Scene Context for Driver Takeover Detection ", as it appears in ICASSP 2022. In the current release, the data is only available for researchers from universities. To obtain the dataset, please follow the following instructions.

Important: The following instructions must be followed exactly:

Please use your official university email to tmisu @ honda-ri dot com to request the agreement.
You will receive a link and password to the data in your official email address after the review.

Citation

This dataset corresponds to two papers. Data based on simulator video corresponds to, Incorporating Gaze Behavior Using Joint Embedding with Scene Context for Driver Takeover Detection, as it appears in the proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP)}. Real video data corresponds to, TBD.

Please cite the following paper if you find this work useful:

@Inproceedings{yqiu2022GazeBehavior,
	title={Incorporating Gaze Behavior Using Joint Embedding With Scene Context for Driver Takeover Detection}, 
	author={Qiu, Yuning and Busso, Carlos and Misu, Teruhisa and Akash, Kumar},
	booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
        pages={4633-4637},
        year={2022}
}