Understanding Drivers’ Stress and Interactions With Vehicle Systems Through Naturalistic Data Analysis

Today, and probably for a long time to come, humans will remain an integral part of vehicles for driving tasks. Therefore, it is essential to understand how vehicles and drivers interact with each other and how drivers’ behavior and physical and mental states affect vehicle performance and traffic safety. This article explores the relationship between driver and vehicle in real-world driving conditions by analyzing large-scale naturalistic data collected from cars and drivers. Specifically, more than 800 hours of driving data from 16 drivers were collected using three different data sources (telematics data, video frames, and physiological data) and two types of analysis were done. The first one analyzes different types of driver-vehicle interactions during driving. The second one investigates the effect of different driving conditions on drivers’ stress and explores the relationship between driver and vehicle in different driving conditions. Our experimental results show that drivers’ physiological signals are correlated with some variables from vehicle kinematics and influenced by drivers’ behavior inside the vehicle. These findings could be used to help manage comfort-related in-vehicle intervention systems and could provide a continuous measure of how different external conditions (traffic, road, weather, etc.) affect drivers.