EEG-based Universal Prediction Model of Emergency Braking Intention for Brain-controlled Vehicles*

Electroencephalogram (EEG)-based prediction of driver emergency braking intention can help develop an assistance system to improve driving safety for brain-controlled vehicles. However, existing studies are focused on how to build an individual detection model for each participant. In this paper, to build a universal model, a convolutional neural network (CNN) is used to extract the features of brain signals and build the universal model. Experimental results from 13 subjects show that the proposed CNN-based method outperforms the linear discriminant analysis (LDA)-based method and has a comparable performance with individual models. This work lays a foundation for future developments of an EEG-based universal model of driver emergency braking intention detection.

[1]  Tzyy-Ping Jung,et al.  EEG-based drowsiness estimation for safety driving using independent component analysis , 2005, IEEE Transactions on Circuits and Systems I: Regular Papers.

[2]  Mohan M. Trivedi,et al.  Driver Behavior and Situation Aware Brake Assistance for Intelligent Vehicles , 2007, Proceedings of the IEEE.

[3]  Anton van den Hengel,et al.  Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Brent Lance,et al.  EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces , 2016, Journal of neural engineering.

[5]  Luzheng Bi,et al.  A novel EEG-based detection method of emergency situations for assistive vehicles , 2017, 2017 Seventh International Conference on Information Science and Technology (ICIST).

[6]  Luzheng Bi,et al.  Using EEG to recognize emergency situations for brain-controlled vehicles , 2015, 2015 IEEE Intelligent Vehicles Symposium (IV).

[7]  Massimo Bertozzi,et al.  Pedestrian detection for driver assistance using multiresolution infrared vision , 2004, IEEE Transactions on Vehicular Technology.

[8]  Leon O. Chua,et al.  Overview of CNN research: 25 years history and the current trends , 2015, 2015 IEEE International Symposium on Circuits and Systems (ISCAS).