Physics Constrained Motion Prediction with Uncertainty Quantification

TL;DR

This paper introduces a physics-constrained motion prediction method that ensures dynamic feasibility and quantifies uncertainty, significantly improving accuracy and safety metrics for autonomous driving.

Contribution

It proposes a novel two-step approach combining intent and trajectory prediction with conformal prediction for uncertainty quantification, ensuring physically feasible and reliable motion forecasts.

Findings

Achieves 41% better ADE over baseline

Achieves 56% better FDE over baseline

Achieves 19% better IoU over baseline

Abstract

Predicting the motion of dynamic agents is a critical task for guaranteeing the safety of autonomous systems. A particular challenge is that motion prediction algorithms should obey dynamics constraints and quantify prediction uncertainty as a measure of confidence. We present a physics-constrained approach for motion prediction which uses a surrogate dynamical model to ensure that predicted trajectories are dynamically feasible. We propose a two-step integration consisting of intent and trajectory prediction subject to dynamics constraints. We also construct prediction regions that quantify uncertainty and are tailored for autonomous driving by using conformal prediction, a popular statistical tool. Physics Constrained Motion Prediction achieves a 41% better ADE, 56% better FDE, and 19% better IoU over a baseline in experiments using an autonomous racing dataset.