Adaptive Conformal Prediction Intervals Over Trajectory Ensembles

TL;DR

This paper introduces a conformal prediction framework that calibrates ensemble trajectory predictions into reliable, adaptive uncertainty intervals with theoretical guarantees, improving temporal dependency modeling.

Contribution

It presents a novel online updating and optimization approach for conformal prediction, enhancing calibration and sharpness of trajectory uncertainty estimates.

Findings

Produces calibrated prediction intervals with coverage guarantees

Captures temporal dependencies in trajectory data

Generates sharper, more adaptive uncertainty estimates

Abstract

Future trajectories play an important role across domains such as autonomous driving, hurricane forecasting, and epidemic modeling, where practitioners commonly generate ensemble paths by sampling probabilistic models or leveraging multiple autoregressive predictors. While these trajectories reflect inherent uncertainty, they are typically uncalibrated. We propose a unified framework based on conformal prediction that transforms sampled trajectories into calibrated prediction intervals with theoretical coverage guarantees. By introducing a novel online update step and an optimization step that captures inter-step dependencies, our method can produce discontinuous prediction intervals around each trajectory, naturally capture temporal dependencies, and yield sharper, more adaptive uncertainty estimates.