# 面向控制的轨迹扩散不确定性

> 原文链接：https://robotics.hellobike.com/papers/2026-10-08-2610-12431
> 频道：papers | 更新日期：2026-10-08 | 标签：arxiv, cs.RO
> 核心摘要：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。

# 面向控制的轨迹扩散不确定性

::: v-pre
> 原文链接：[Control-Ready Uncertainty for Trajectory Diffusion](https://arxiv.org/abs/2610.12431)（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
:::

## 原始参考来源 (Sources)

- [arXiv 2610.12431：Control-Ready Uncertainty for Trajectory Diffusion](https://arxiv.org/abs/2610.12431)