Passenger hazard perception based on EEG signals for highly automated driving vehicles

TL;DR

This paper presents a neural network-based approach using EEG signals to predict passenger hazard perception in highly automated vehicles, aiming to improve safety by integrating human neural responses with autonomous systems.

Contribution

It introduces a novel Passenger EEG Decoding Strategy with a CRNN model that effectively captures EEG patterns to predict hazard perception, advancing human-vehicle interaction safety.

Findings

CRNN achieves 85% accuracy in hazard detection

Pre-event EEG data significantly predicts hazard perception

Network-driven framework enhances autonomous vehicle safety

Abstract

Enhancing the safety of autonomous vehicles is crucial, especially given recent accidents involving automated systems. As passengers in these vehicles, humans' sensory perception and decision-making can be integrated with autonomous systems to improve safety. This study explores neural mechanisms in passenger-vehicle interactions, leading to the development of a Passenger Cognitive Model (PCM) and the Passenger EEG Decoding Strategy (PEDS). Central to PEDS is a novel Convolutional Recurrent Neural Network (CRNN) that captures spatial and temporal EEG data patterns. The CRNN, combined with stacking algorithms, achieves an accuracy of $85.0\% \pm 3.18\%$. Our findings highlight the predictive power of pre-event EEG data, enhancing the detection of hazardous scenarios and offering a network-driven framework for safer autonomous vehicles.