用扩散模型融合历史与实时信息，生成稳定可控的自动驾驶轨迹
Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving
- 分段处理历史、当前和未来轨迹，不同噪声水平协同去噪
- 通过渐变历史引导未来采样，实现平滑连续的运动规划
- 适合复杂城市驾驶场景，提升轨迹稳定性和安全性
基于学习的运动规划器虽有进展，但仍面临时间不一致问题。帧间微小扰动会累积成不稳定轨迹，影响闭环驾驶的舒适性与安全性。现有方法将历史作为静态条件信号注入，导致规划器复制历史模式而无法适应环境变化。为此，我们提出扩散强制规划器（DFP），一种基于扩散模型的规划框架，以历史引导控制为核心。具体地，DFP将完整轨迹分解为历史、当前和未来三段，并为每段分配独立的噪声水平，联合去噪形成异构扩散过程。推理时，采用无分类器引导（CFG）以渐进式历史信息可控地引导未来采样。在nuPlan上的闭环评估与全面消融实验表明，DFP在复杂驾驶场景中实现了性能竞争力的同时，生成了连续、稳定且可控制的运动规划。
原文摘要 · Abstract (English)
Learning-based motion planners, despite recent progress, often suffer from temporal inconsistency. Small perturbations across frames can accumulate into unstable trajectories, degrading comfort and safety in closed-loop driving. Several methods attempt to inject history as a static conditioning signal to stabilize outputs, only to induce the planner to copy historical patterns instead of adapting to environment contexts. To address this limitation, we propose Diffusion Forcing Planner (DFP), a diffusion-based planning framework driven by history-guided control. Specifically, DFP decomposes the full trajectory into history, current and future segments, and assign independent noise levels to each segment. The model jointly denoises the historical and the future segments, enforcing a heterogeneous joint diffusion process. At inference, classifier-free guidance (CFG) is applied to steer future sampling using annealed history in a controllable manner. Closed-loop evaluation and comprehensive ablations on nuPlan show that DFP achieves competitive performance while producing continuous, stable, and controllable motion plans in complex driving scenarios.
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。