Decoding Passenger's EEG Signals From Encountering Emergency Road Events.

In this paper, we analyzed passengers' electroencephalography (EEG) signals to distinguish between emergency and non-emergency events. 64-Channel EEG signals of 9 participants were collected when they were watching a simulated driving video with pedestrians standing on the right side of the road and suddenly crossing the street, from the front passenger seat point of view. Event-related potential (ERP) and machine learning techniques were used to analyze and classify the signals of two road events. Results show that the responses are 454 +/- 234 ms before the reaction, and the average recognition accuracy of the regularized linear discriminant analysis (RLDA) classifier reached 95.81%. We also verified our findings in a real-car automatic emergency braking (AEB) experiment. It is the first study to investigate a passenger's EEG signals of emergency situations during simulated and real-world autonomous driving experiments. Overall, the results illustrate that EEG-based human-centric assistant driving systems have the potential of being deployed in high-level autonomous vehicles to enhance the safety of passengers and overall public safety.