标题： 噪声感知的生成微观交通仿真 显示英文标题

标题： Noise-Aware Generative Microscopic Traffic Simulation

摘要： 在微观交通仿真中准确建模个体车辆行为仍然是智能交通系统中的一个关键挑战，因为它要求车辆能够真实地生成和响应复杂的交通现象，如幽灵交通拥堵。 虽然传统的驾驶员模拟模型提供了计算上的可行性，但这是通过抽象掉定义人类驾驶的复杂性来实现的。 另一方面，基于安装在基础设施上的摄像头的道路感知技术的最新进展，使得可以提取车辆轨迹数据，这为转向生成式、基于代理的模型提供了机会。 然而，一个主要的瓶颈仍然存在：大多数现有数据集要么过于干净，要么缺乏标准化，无法反映现实世界感知的噪声和不完美特性。 与车载传感器的数据不同——车载传感器可以通过重叠的视野和传感器融合来减轻遮挡等感知伪影——基于基础设施的传感器呈现出更混乱、更实际的视角，反映了交通工程师遇到的挑战。 为此，我们提出了I-24 MOTION场景数据集（I24-MSD）——一个标准化的、经过筛选的数据集，旨在保留一定程度的传感器不完美性，将这些错误视为学习问题的一部分，而不是仅仅通过预处理来克服的障碍。 借鉴计算机视觉中的噪声感知学习策略，我们进一步调整了自动驾驶社区中现有的生成模型，以适应I24-MSD，并使用噪声感知损失函数。 我们的结果表明，这些模型不仅在现实性方面优于传统基线，而且通过明确参与而非抑制数据不完美性而受益。 我们认为I24-MSD是迈向新一代微观交通仿真的一块基石，它接受现实世界的挑战，并更好地与实际需求对齐。 显示英文摘要

摘要： Accurately modeling individual vehicle behavior in microscopic traffic simulation remains a key challenge in intelligent transportation systems, as it requires vehicles to realistically generate and respond to complex traffic phenomena such as phantom traffic jams. While traditional human driver simulation models offer computational tractability, they do so by abstracting away the very complexity that defines human driving. On the other hand, recent advances in infrastructure-mounted camera-based roadway sensing have enabled the extraction of vehicle trajectory data, presenting an opportunity to shift toward generative, agent-based models. Yet, a major bottleneck remains: most existing datasets are either overly sanitized or lack standardization, failing to reflect the noisy, imperfect nature of real-world sensing. Unlike data from vehicle-mounted sensors-which can mitigate sensing artifacts like occlusion through overlapping fields of view and sensor fusion-infrastructure-based sensors surface a messier, more practical view of challenges that traffic engineers encounter. To this end, we present the I-24 MOTION Scenario Dataset (I24-MSD)-a standardized, curated dataset designed to preserve a realistic level of sensor imperfection, embracing these errors as part of the learning problem rather than an obstacle to overcome purely from preprocessing. Drawing from noise-aware learning strategies in computer vision, we further adapt existing generative models in the autonomous driving community for I24-MSD with noise-aware loss functions. Our results show that such models not only outperform traditional baselines in realism but also benefit from explicitly engaging with, rather than suppressing, data imperfection. We view I24-MSD as a stepping stone toward a new generation of microscopic traffic simulation that embraces the real-world challenges and is better aligned with practical needs.