Driver Behavior Estimation at Signalized Intersections Using a Physics-Constrained Decision-Conditioned Autoregressive Transformer
Driver Behavior Estimation at Signalized Intersections Using a Physics-Constrained Decision-Conditioned Autoregressive Transformer
基于物理约束与决策条件自回归 Transformer 的信号交叉口驾驶行为估计
Abstract: Red-light violations and harsh braking at signalized intersections are major contributors to traffic accidents. This paper analyzes and predicts human driver decision-making and longitudinal trajectory behavior during traffic light signal transitions. 摘要： 信号交叉口的闯红灯行为和急刹车是导致交通事故的主要因素。本文分析并预测了人类驾驶员在交通信号灯转换期间的决策制定过程及纵向轨迹行为。
We collected a diverse real-world dataset comprising 449 approach runs under varying speed and distance conditions. Vehicle motion was recorded using RTK-corrected GNSS with centimeter-level accuracy, and driver heart rate and multi-level comfort ratings were monitored. Spatial and temporal calibration ensured precise alignment between vehicle state and signal timing. 我们收集了一个多样化的真实世界数据集，包含在不同速度和距离条件下的 449 次接近路口行驶记录。车辆运动数据通过具有厘米级精度的 RTK 校正 GNSS 记录，同时监测了驾驶员的心率和多级舒适度评分。空间和时间校准确保了车辆状态与信号灯时序之间的精确对齐。
Statistical analysis identifies required deceleration as the dominant single predictor of the stop-go decision, and heteroscedastic Gaussian modeling of peak deceleration reveals five empirical comfort ranges derived from human stopping behavior. 统计分析表明，所需减速度是决定“停车-通行”决策的主要单一预测指标；通过对峰值减速度进行异方差高斯建模，揭示了源自人类停车行为的五个经验舒适度区间。
Based on this insight, we propose a two-stage modeling framework. Stage 1 predicts the binary maneuver decision, and Stage 2 generates the longitudinal acceleration trajectory using a decision-conditioned autoregressive Transformer with physics constraints, including target-state conditioning and jerk limits. 基于这一洞察，我们提出了一个两阶段建模框架。第一阶段预测二元操作决策，第二阶段使用带有物理约束（包括目标状态条件和加加速度限制）的决策条件自回归 Transformer 生成纵向加速度轨迹。
The proposed architecture outperforms baseline methods and achieves 0.49m/s^2 acceleration MAE and 0.62m distance MAE. It also estimates the future stopping-comfort level of the human driver from a single yellow-onset snapshot. Qualitative results demonstrate realistic human-like braking behavior. The dataset and source code are publicly available. 所提出的架构优于基准方法，实现了 0.49m/s² 的加速度平均绝对误差 (MAE) 和 0.62m 的距离 MAE。它还能仅凭黄灯亮起瞬间的快照，估计人类驾驶员未来的停车舒适度水平。定性结果证明了其具备逼真的人类驾驶刹车行为。数据集和源代码已公开。