Uncertainty-Aware Optimization for Physics-Aware Highway Trajectory Prediction

2026-10-08

AI Summary

Existing trajectory prediction methods fail to explicitly propagate the uncertainty of motion variables into the trajectory space, rendering predictions unable to reflect underlying dynamical variations. This work proposes an uncertainty-aware extension of the X-TRACK framework that, for the first time, integrates physical models with aleatoric and epistemic uncertainty modeling. By employing deep ensembles and Monte Carlo Dropout, it achieves the physics-based propagation of motion uncertainty into the trajectory space, while leveraging conformal prediction to construct uncertainty regions with statistical guarantees. Experiments on the highD dataset demonstrate that the proposed method not only improves prediction accuracy but also yields reliable uncertainty quantification consistent with target coverage rates.

Abstract

Accurate trajectory forecasting and well-defined predictive uncertainty are crucial for reliable, safety-critical applications such as autonomous driving. Most trajectory prediction approaches provide point estimates only, while uncertainty-aware approaches typically quantify uncertainty only in the trajectory space. In physics-aware approaches, uncertainty in the predicted motion variables should be explicitly modeled and propagated through the vehicle dynamics. Otherwise, the resulting trajectory-space uncertainty may not fully reflect the variability introduced by the underlying motion prediction. Therefore, in this work, uncertainty-aware extensions of X-TRACK (X-TRACK-DE and X-TRACK-MCD), a physics-aware trajectory prediction framework, are proposed. The proposed framework predicts future vehicle motion variables and models both aleatoric and epistemic uncertainties by propagating motion space uncertainty to trajectory space. Additionally, conformal prediction is applied to the trajectory space predictive covariance to construct uncertainty regions targeting a desired marginal coverage level. Evaluation on the highD dataset shows that X-TRACK-DE improves trajectory prediction accuracy over the deterministic baseline, while both uncertainty-aware variants provide predictive uncertainty that can be conformally calibrated to the desired marginal coverage level.

Problem

• trajectory prediction
• uncertainty quantification
• physics-aware
• autonomous driving
• conformal prediction

Innovation

• Uncertainty-Aware Trajectory Prediction
• Physics-Aware Modeling
• Conformal Prediction
• Aleatoric and Epistemic Uncertainty
• Autonomous Driving