外观
论文arXiv 2610.1243120 天前
面向控制的轨迹扩散不确定性
针对扩散轨迹模型不确定性提取开销高，提出 SCOPE 生成高斯管，并在预测、导航、控制与真机操作中验证。
Franka FR3原文链接：Control-Ready Uncertainty for Trajectory Diffusion（arXiv 2610.12431 · 发布日期：2026-10-08）
Control-Ready Uncertainty for Trajectory Diffusion
针对扩散轨迹模型不确定性提取开销高，提出 SCOPE 生成高斯管，并在预测、导航、控制与真机操作中验证。
核心要点
- 扩散模型可表征多模态轨迹，但蒙特卡洛采样提取不确定性开销高，限制实时控制。
- SCOPE 蒸馏 score-curvature 信息，在每条标称轨迹周围学习结构化精度矩阵。
- 方法以低开销输出校准高斯管和逐时刻协方差，无需重复蒙特卡洛采样。
- 在行人预测、拥挤导航、Maze2D 控制和真实 Franka Panda 操作中获得更好闭环表现。
验证范围与局限：验证范围包括行人预测、拥挤导航、Maze2D 控制和真实 Franka Panda 操作。
英文摘要 (Abstract)
Diffusion models can represent complex, multimodal trajectory distributions, but extracting uncertainty from them typically requires costly Monte Carlo sampling. This limits their use in real-time control, where robots must rapidly assess risk and maintain safety margins. We introduce Score-Curvature for Online Precision Estimation (SCOPE), a lightweight module that augments diffusion trajectory models with control-ready uncertainty. SCOPE learns a structured precision matrix around each nominal trajectory by distilling score-curvature information and producing calibrated Gaussian tubes with low overhead and without repeated Monte Carlo sampling. These tubes provide per-timestep covariance estimates that can be used both as predicted occupancy for moving agents and as adaptive exploration guides for robot control. We evaluate SCOPE with mode-conditioned multimodal diffusion backbones in pedestrian forecasting, crowd navigation, Maze2D control, and real-world Franka Panda manipulation. Across these settings, SCOPE provides fast uncertainty estimation, which leads to better closed-loop performance. Project page: https://zackaxue.github.io/SCOPE-project-page/
作者：Zhiwei Xue, Jia Yue Kam, Jinhang Qiu, Yifeng Cheng, Ege Gursoy, Jiaming Wang, Vincent Bonnet, Harold Soh
来源
本页事实对应的公开页面，以原文为准。