用扩散模型生成可交互的交通场景，提升效率与可控性。
Proposal-Conditioned Latent Diffusion for Closed-Loop Traffic Scenario Generation
- 基于实例场景和多模态提议条件生成，提升采样效率。
- 在Waymo数据集上实现真实感、安全性和可控性的平衡。
- 支持运行时引导，灵活调整安全与行为目标权衡。
闭环交通模拟仍具挑战性，需生成与场景一致且可控制的多智能体交互行为。现有基于扩散模型的方法虽具高真实感，但计算成本高，难以在自动驾驶规划的实时重规划环中部署。本文提出一种基于扩散的场景生成框架，以实例为中心的场景上下文和多模态提议先验为条件，并支持运行时引导以塑造关键安全行为。采用紧凑的动作-隐空间表示与基于提议的初始化，在不重新训练的前提下显著提升采样效率并降低每步推理时间。在Waymo Open Motion Dataset上的实验表明，该方法在多样化交互场景中实现了真实感、安全性与可控性的良好平衡，且运行时引导可系统性调节多个竞争目标之间的权衡。
原文摘要 · Abstract (English)
Closed-loop traffic simulation remains challenging because it must generate interactive multi-agent behaviors that are scene-consistent and controllable throughout rollout. Prior diffusion-based approaches achieve strong realism, but their computational cost can hinder deployment in time-constrained replanning loops for autonomous vehicle planning and simulation. We present a diffusion-based scenario generation framework conditioned on instance-centric scene context and multimodal proposal priors, with optional test-time guidance for shaping safety-critical behaviors. A compact action-latent representation and proposal-based initialization improve sampling efficiency and reduce per-step runtime without retraining. Experiments on the Waymo Open Motion Dataset demonstrate a favorable balance among realism, safety, and controllability across diverse interactive scenarios, while showing that test-time guidance enables systematic trade-offs among competing objectives.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。