Towards safe autonomous driving (AD), we consider the problem of learning models that accurately capture the diversity and tail quantiles of human driver behavior probability distributions, in interaction with an AD vehicle. Such models, which predict drivers' continuous actions from their states, are particularly relevant for closing the gap between AD simulation and reality. To this end, we adapt two flexible frameworks for this setting that avoid strong distributional assumptions: (1)~quantile regression (based on the titled absolute loss), and (2)~autoregressive quantile flows (a version of normalizing flows). Training happens in a behavior cloning-fashion. We evaluate our approach in a one-step prediction, as well as in multi-step simulation rollouts. We use the highD dataset consisting of driver trajectories on several highways. We report quantitative results using the tilted absolute loss as metric, give qualitative examples showing that realistic extremal behavior can be learned, and discuss the main insights.

翻译：为实现安全自动驾驶，我们研究了如何学习能够准确捕捉人类驾驶员行为概率分布的多样性及尾部分位数的模型（该模型在与自动驾驶车辆交互的场景下建立）。这类模型通过驾驶员状态预测其连续动作，对于弥合自动驾驶仿真与现实差距具有关键意义。为此，我们针对该场景调整了两种避免强分布假设的灵活框架：（1）分位数回归（基于倾斜绝对损失函数）和（2）自回归分位数流（归一化流的一种变体）。训练采用行为克隆范式。我们通过单步预测和多步仿真轨迹展开两种方式评估所提方法，使用包含多条高速公路驾驶员轨迹的highD数据集，并以倾斜绝对损失函数作为量化指标报告结果。定性案例表明模型可学习真实极端行为，最后讨论主要发现。