Human driver errors, such as distracted driving, inattention, and aggressive driving, are the leading causes of road accidents. Understanding the underlying factors that contribute to these behaviors is critical for improving road safety. Previous studies have shown that physiological states, like raised heart rates due to stress and anxiety, can influence driving behavior, leading to erratic driving behaviors and an increased risk of accidents.
In this study, we conducted on-road tests using a measurement system based on the Driver-Driven vehicle-Driving environment (3D) method. We collected physiological signals, specially electrocardiogram (ECG) data, from human drivers to examine the relationship between physiological states and driving behaviors. The aim was to determine whether ECG could serve as an indicator of potential risky driving behaviors, such as sudden acceleration and frequent steering adjustments. This information could enable automated driving systems (AD) to intervene in dangerous driving situations.
Measurements were collected from 22 participants, each tested for 15 minutes on the highway, resulting in a dataset of 330 minutes of physiological data and over 500 km of driving data. The data was segmented into 20-second intervals for detailed analysis. Each segment was labeled twice: physiological states classified as “high” or “low” based on heart rate derived from ECG, and driving styles categorized as “defensive”, “average”, or “sporty” based on CAN-Bus data. Preliminary findings revealed a significant correlation between overall driving styles and physiological states. We also explored individual driving parameters, including velocity, acceleration, steering patterns, etc. For example, segments labeled as “high” showed an average velocity 5.4% above baseline, while segments labeled as “low” were 5% below baseline. This study focuses on how physiological signals changed during aggressive driving and aims to establish these signals as indicators for alerting drivers, ultimately reducing the risks of accident associated with aggressive driving behaviors.