Diffusion-based trajectory planners can synthesize rich, multimodal robot motions, but their iterative denoising makes online planning and control prohibitively slow. Existing accelerations either modify the sampler or compress the network--sacrificing plan quality or requiring retraining without accounting for downstream control risk. We address the problem of making diffusion-based trajectory planners fast enough for real-time robot use without retraining the model or sacrificing trajectory quality, and in a way that works across diverse state-space diffusion architectures. Our key insight is that diffusion trajectory planners expose two signals we can exploit: a cheap probe of how their internal trajectory representation changes across steps, and analytic coefficients that describe how denoiser errors affect the sampler's state update. By calibrating the first signal against the second on offline runs, we obtain a per-step score that upper-bounds how far the final trajectory can deviate when we reuse a cached denoiser output, and we treat this bound as an uncertainty budget that we can spend over the denoising process. Building on this insight, we present Muninn, a training-free caching wrapper that tracks this uncertainty budget during sampling and, at each diffusion step, chooses between reusing a cached denoiser output when the predicted deviation is small and recomputing the denoiser when it is not. Across standard benchmarks Muninn delivers up to 4.6x wall-clock speedups across several trajectory diffusion models by reducing denoiser evaluations, while preserving task performance and safety metrics. Muninn further certifies that cached rollouts remain within a specified distance of their full-compute counterparts, and we validate these gains in real-time closed-loop navigation and manipulation hardware deployments. Project page: https://github.com/gokulp01/Muninn.

翻译：基于扩散的轨迹规划器能够合成丰富、多模态的机器人运动，但其迭代去噪过程使得在线规划和控制速度过慢，难以实用。现有加速方法要么修改采样器，要么压缩网络——牺牲规划质量或需要重新训练且不考虑下游控制风险。我们解决了在不重新训练模型或不牺牲轨迹质量的前提下，使基于扩散的轨迹规划器足够快以用于实时机器人任务的问题，且该方法适用于多种状态空间扩散架构。我们的核心洞察是：扩散轨迹规划器暴露了两种可利用的信号——一种低成本探针，用于衡量其内部轨迹表示在步骤间的变化；以及描述去噪器误差如何影响采样器状态更新的解析系数。通过在离线运行中用第二种信号校准第一种信号，我们获得了一个逐步骤得分，该得分给出了当重用缓存的去噪器输出时最终轨迹可能偏离的上界，并将此上界视为可在去噪过程中花费的不确定性预算。基于这一洞察，我们提出了Muninn，一种无需训练即可用的缓存封装器，在采样过程中跟踪此不确定性预算，并在每个扩散步骤中根据预测偏差大小选择重用缓存去噪器输出（当偏差较小时）或重新计算去噪器（当偏差较大时）。在标准基准测试中，Muninn通过减少去噪器评估次数，在多个轨迹扩散模型上实现了高达4.6倍的时钟时间加速，同时保持了任务性能和安全指标。Muninn还能确保缓存的轨迹 rollout 与完全计算版本保持在指定距离内，我们在实时闭环导航与操作硬件部署中验证了这些增益。项目页面：https://github.com/gokulp01/Muninn。