Stochasticity in Motion: An Information-Theoretic Approach to Trajectory Prediction

TL;DR

This paper introduces an information-theoretic framework for trajectory prediction in autonomous driving that quantifies and decomposes uncertainty into aleatoric and epistemic components, enhancing safety and robustness.

Contribution

It presents a novel, theoretically grounded method for uncertainty decomposition compatible with existing motion predictors, improving uncertainty estimation in trajectory prediction.

Findings

Effective uncertainty decomposition demonstrated on nuScenes dataset

Model architecture influences uncertainty quantification

Enhanced robustness through better uncertainty understanding

Abstract

In autonomous driving, accurate motion prediction is crucial for safe and efficient motion planning. To ensure safety, planners require reliable uncertainty estimates of the predicted behavior of surrounding agents, yet this aspect has received limited attention. In particular, decomposing uncertainty into its aleatoric and epistemic components is essential for distinguishing between inherent environmental randomness and model uncertainty, thereby enabling more robust and informed decision-making. This paper addresses the challenge of uncertainty modeling in trajectory prediction with a holistic approach that emphasizes uncertainty quantification, decomposition, and the impact of model composition. Our method, grounded in information theory, provides a theoretically principled way to measure uncertainty and decompose it into aleatoric and epistemic components. Unlike prior work, our approach is compatible with state-of-the-art motion predictors, allowing for broader applicability. We demonstrate its utility by conducting extensive experiments on the nuScenes dataset, which shows how different architectures and configurations influence uncertainty quantification and model robustness.