发表机构
National University of Singapore; Smart Systems Institute, NUS; LAAS-CNRS（新加坡国立大学; 新加坡国立大学智能系统研究所; 法国国家科学研究中心自动化与系统分析实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对扩散模型提取不确定性需高代价蒙特卡洛采样的问题，提出轻量级模块SCOPE，为轨迹扩散模型增添可控制不确定性，在多任务评估中实现快速不确定性估计并提升闭环性能。
AI 中文摘要
扩散模型能够表示复杂、多模态的轨迹分布，但从其中提取不确定性通常需要代价高昂的蒙特卡洛采样，这限制了它们在实时控制中的应用，而机器人在实时控制中必须快速评估风险并保持安全裕度。我们引入了用于在线精度估计的Score-Curvature（SCOPE），这是一个轻量级模块，可为扩散轨迹模型增添可控制的不确定性。SCOPE通过提炼得分曲率信息，围绕每个标称轨迹学习结构化精度矩阵，生成校准的高斯管，其开销低且无需重复的蒙特卡洛采样。这些高斯管提供每时间步的协方差估计，既可用作移动智能体的预测占用，也可用作机器人控制的自适应探索引导。我们在行人预测、人群导航、Maze2D控制以及真实世界的Franka Panda操作中，使用基于模式条件的多模态扩散骨干网络对SCOPE进行评估。在所有这些设置中，SCOPE都能提供快速的不确定性估计，从而带来更好的闭环性能。项目页面：this https URL
英文摘要
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/
CommentsAccepted at the Conference on Robot Learning (CoRL) 2026 as a Spotlight presentation. 39 pages, 12 figures
