Investigating the Influence of ADAS on Drivers’ Evasive Behaviors During Car-Following on Highways

Paper i proceeding, 2022

Various advanced driving assistance systems (ADAS) are designed to help drivers make reasonable evasive decisions in emergency conditions. However, different drivers have different perceptions of driving risks, resulting in differences in the choice of evasive behaviors (e.g., car-following, overtaking, etc.). To explorer the impact of ADAS on vehicle interaction behaviors under dangerous conditions, this study objectively assessed how ADAS affected drivers’ choice of evasive behaviors in near-crash events (NCEs). An on-road experiment was conducted on public highways in real traffic. The dangerous driving data of NCEs in different working states of ADAS (i.e., activated or not) were collected and combined to classify NCEs’ risk levels: lower, medium, and higher based on the K-means clustering results. Drivers’ evasive behaviors during ADAS engagement (i.e., during the use of the forward collision warning system) were then found closely associated with NCEs’ risk levels. Differences of probabilities for evasive behaviors were further compared within and across the three risk groups. Results showed that ADAS engagement has a positive impact on reducing the occurrence of NCEs and reduces the probability that drivers in medium and high-risk groups choose overtaking behavior. ADAS engagement can help drivers maintain a greater time headway (THW) when taking evasive action. Findings in this study could optimize ADAS intervention strategies and further enhance the ability of safe driving assistance.