扩散强制规划器：面向自动驾驶的历史退火规划与时变引导
Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving
把扩散模型的分段独立噪声水平与 CFG 结合，用退火历史作为引导信号来抑制时序抖动；做端到端轨迹生成或视频/序列预测的研究者可借鉴这种「历史段与未来段联合去噪」的异构扩散设定。
原文依据 DFP decomposes the full trajectory into history, current and future segments, and assign independent noise levels to each segment.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于学习的运动规划器尽管近期取得进展，却常常受困于时序不一致性。跨帧的小扰动会累积成不稳定的轨迹，从而降低闭环驾驶中的舒适性与安全性。若干方法尝试将历史作为静态条件信号注入以稳定输出，结果却诱导规划器复制历史模式，而非适应环境上下文。为应对这一局限，我们提出扩散强制规划器（DFP），一个由历史引导控制驱动的基于扩散的规划框架。具体而言，DFP 将完整轨迹分解为历史、当前与未来三段，并为每一段分配独立的噪声水平。模型对历史段与未来段进行联合去噪，从而形成一种异构联合扩散过程。在推理阶段，应用无分类器引导（CFG），以退火后的历史以可控方式引导未来采样。在 nuPlan 上的闭环评测与全面消融实验表明，DFP 在复杂驾驶场景中取得了有竞争力的性能，同时生成连续、稳定且可控的运动规划。
英文原文摘要 1164 字符
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.