Behavioral classification of drivers in car-following situations: safe, defensive, risky, aggressive

Engineering notes

Key topics: autonomous driving, perception. See the paper for implementation details and experimental results.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

A driver’s perception of safety plays a crucial role in shaping driving behavior during critical situations. In car-following scenarios involving critical events, however, this perception may not always align with actual crash risk, thereby increasing the crash risk. This study examined how sociodemographic factors and driving conditions including leading vehicle type, and speed limits influence the behavioral classification of drivers based on safety perception alignment in car-following scenarios. Data from 61 participants were collected in a driving simulator across eight scenarios. Subjective safety perceptions were compared with objective safety metrics to classify drivers into four behavioral categories: Safe, Defensive, Risky, and Aggressive. Mixed Effect Multinomial logistic regression revealed that drivers with less experience (2–5 years) were more likely to be in the risky category than more experienced drivers. Being in the risky category was also more prevalent at lower speeds and when following motorbike compared to truck. Arab drivers showed a higher likelihood of being in the Aggressive category, while drivers following sedan or SUV were less likely to be classified as aggressive compared to those following a truck. Furthermore, leading vehicle type was found to influence the likelihood of being in the defensive category. These findings provide insights that may support the development of targeted driver training programs and traffic safety interventions tailored to specific driver profiles and driving conditions, ultimately contributing to improved road safety.

Links and sources

• PDF from original source

Comments