发表机构
University of Waterloo（滑铁卢大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出TrafficDiffuser框架，联合建模初始与目标状态对生成高级交通场景，在Argoverse 2数据集上验证，其智能体初始化性能优于次优方法，可降低速度分布距离与越野率。
AI 中文摘要
鲁棒的交通模拟器对于开发和测试自动驾驶车辆至关重要，它可减少成本高昂、劳动密集型的现实世界数据采集过程，以及减少道路上的物理存在需求。然而，现有模拟器需要智能体的初始状态来生成轨迹，由于给定初始状态的限制，这限制了可扩展性和多样性。尽管数据驱动的智能体初始化已被广泛研究，但生成的初始状态在智能体为何被初始化在那些特定位置方面缺乏可解释性。在已知初始状态的情况下，轨迹生成也是一个具有挑战性的问题，因为模型必须学习目的地的变异性以及智能体应如何随时间到达目的地。在本文中，我们提出TrafficDiffuser，一个自上而下的交通场景生成框架，通过联合建模初始和目标状态对来生成由初始-目标状态对定义的高级交通场景。高级场景生成使初始状态更具可解释性，并将轨迹生成简化为一个填充问题。我们展示了生成的高级交通场景的用途，包括基于不同轨迹模式进行约束以及将其与现有轨迹生成模型集成。我们在Argoverse 2运动预测数据集上进行了广泛实验，以评估生成的输出捕获现实世界分布的程度。除了生成目标状态外，TrafficDiffuser在智能体初始化方面优于次优方法，将速度分布距离降低了55.3%，并将越野率降低了2.8%。
英文摘要
Robust traffic simulators are crucial for developing and testing autonomous vehicles to reduce the costly, labor-intensive real-world data collection process and the need for physical presence on the road. However, existing simulators require agents' initial states to generate trajectories, which limits scalability and diversity due to restrictions on the given initial states. While data-driven agent initialization has been widely studied, the generated initial states are not interpretable in terms of why the agents are initialized at those specific locations. Given known initial states, trajectory generation is also a challenging problem, as the model must learn the variability of the destination and how agents should reach it over time. In this paper, we propose TrafficDiffuser, a top-down traffic scenario generation framework that generates high-level traffic scenarios, defined by initial and goal state pairs, by jointly modeling them. The high-level scenario generation makes initial states better interpretable and reduces trajectory generation into as simple as an infilling problem. We demonstrate how the generated high-level traffic scenarios can be used, including constraining based on different trajectory modes and integrating them with existing trajectory generation models. We conduct extensive experiments on the Argoverse 2 motion prediction dataset to evaluate how well the generated outputs capture real-world distributions. In addition to generating goal states, TrafficDiffuser outperforms the next-best approach for agent initialization, reducing speed distribution distance by 55.3% and the off-road rate by 2.8%.
CommentsAccepted for publication at the IEEE International Conference on Intelligent Transportation Systems (ITSC), 2026
