Learning to Predict Vehicle Trajectories with Model-based Planning

TL;DR

This paper introduces PRIME, a novel model-based prediction framework for vehicle trajectories that guarantees feasibility and improves accuracy in autonomous driving scenarios.

Contribution

PRIME combines model-based trajectory generation with learning-based evaluation to produce feasible, accurate, and robust vehicle trajectory predictions.

Findings

PRIME outperforms state-of-the-art methods on Argoverse benchmark.

PRIME guarantees trajectory feasibility under explicit constraints.

PRIME demonstrates robustness under imperfect tracking conditions.

Abstract

Predicting the future trajectories of on-road vehicles is critical for autonomous driving. In this paper, we introduce a novel prediction framework called PRIME, which stands for Prediction with Model-based Planning. Unlike recent prediction works that utilize neural networks to model scene context and produce unconstrained trajectories, PRIME is designed to generate accurate and feasibility-guaranteed future trajectory predictions. PRIME guarantees the trajectory feasibility by exploiting a model-based generator to produce future trajectories under explicit constraints and enables accurate multimodal prediction by utilizing a learning-based evaluator to select future trajectories. We conduct experiments on the large-scale Argoverse Motion Forecasting Benchmark, where PRIME outperforms the state-of-the-art methods in prediction accuracy, feasibility, and robustness under imperfect tracking.