Control-Ready Uncertainty for Trajectory Diffusion

2026-10-08

AI Summary

This study addresses the reliance of diffusion models on Monte Carlo sampling for uncertainty extraction, which impedes real-time robotic control. To overcome this limitation, we propose the SCOPE module, which distills score curvature information to generate structured precision matrices without repeated sampling. This approach constructs lightweight and well-calibrated Gaussian uncertainty tubes for trajectory diffusion models, enabling low-overhead stepwise covariance estimation and adaptive exploration guidance. We evaluate SCOPE across pedestrian prediction, crowd navigation, and robotic manipulation tasks. Experimental results demonstrate that our method significantly accelerates uncertainty quantification while effectively enhancing closed-loop safe control performance.

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/

Problem

• diffusion models
• trajectory uncertainty
• real-time control
• Monte Carlo sampling
• risk assessment

Innovation

• Diffusion Models
• Uncertainty Estimation
• Score Curvature
• Trajectory Prediction
• Robot Control