AI 中文总结
研究从驾驶员行为信号估计交通复杂性的逆推理问题，通过筛选五个领域的行为特征，经混合效应方差分解发现复杂性仅解释少量行为方差，引导注视率是关键特征，结果为系统定义部署模式并指出方差结构是复杂性估计瓶颈。
AI 中文摘要
理解交通状况对人类驾驶员具有挑战性的原因对于安全舒适的部分自动驾驶至关重要。现有复杂性指标仅表征外部环境因素，而驾驶员监测系统仅检测分心等内源性状态。双方都未捕捉到外部需求如何转化为驾驶员感知的情境负荷。驾驶员行为是两者之间的自然桥梁，本文研究从行为信号估计交通复杂性的逆推理问题。对来自20名驾驶员在实际城市交通中的数据应用了对五个领域（注视、头部姿势、纵向控制、引导注视、扫描策略）的175个行为特征的系统筛选。其中31个特征显示出统计学上确认的复杂性影响，140个通过等效性测试确认为零效应。混合效应方差分解表明，复杂性仅解释了1.5%的行为方差，而驾驶员身份占23%，剩余方差占75%。这种不利比例解释了所有八种评估的特征级个性化策略的失败以及在留一法交叉验证下四种分类架构在F1约为0.45时的收敛。引导注视率成为最适合部署的单一特征，结合了速度稳健性、驾驶员通用性以及复杂性敏感性方面最小的驾驶员间差异。结果为复杂性自适应高级驾驶员辅助系统定义了三种部署模式，并将方差结构确立为复杂性估计的主要瓶颈。
英文摘要
Understanding why a traffic situation is demanding for the human driver is central to safe and comfortable partially automated driving. Existing complexity metrics characterize only external environmental factors, while driver monitoring systems detect only endogenous states such as distraction. Neither side captures how external demands translate into driver-perceived situational load. Driver behavior serves as the natural bridge between both, and this paper investigates the inverse inference problem of estimating traffic complexity from behavioral signals. A systematic screening of 175 behavioral features across five domains (gaze, head pose, longitudinal control, guiding fixation, scanning strategy) is applied to data from 20 drivers in real urban traffic. Of these, 31 features exhibit statistically confirmed complexity effects, while 140 are confirmed as null effects through equivalence testing. Mixed-effects variance decomposition reveals that complexity explains only 1.5% of behavioral variance, whereas driver identity accounts for 23% and residual variance for 75%. This unfavorable ratio explains both the failure of all eight evaluated feature-level personalization strategies and the convergence of four classification architectures at F1 around 0.45 under leave-one-subject-out cross-validation. Guiding fixation rate emerges as the single most deployment-ready feature, combining speed-robustness, universality across drivers, and minimal inter-driver variation in complexity sensitivity. The results define three deployment regimes for complexity-adaptive advanced driver assistance systems and establish the variance structure as the primary bottleneck for complexity estimation.
CommentsThis work has been submitted to the IEEE for possible publication
