ProDrive: Proactive Planning for Autonomous Driving via Ego-Environment Co-Evolution

TL;DR

ProDrive introduces a proactive planning framework for autonomous driving that models future scene evolution and jointly trains a trajectory planner with a world model for safer, more efficient decisions.

Contribution

It presents a novel ego-environment co-evolution approach with end-to-end training, enabling proactive planning beyond current observations.

Findings

ProDrive outperforms baselines in safety and efficiency on NAVSIM v1.

Ego-environment coupling improves planning outcomes.

Bidirectional training preserves gradient flow for better decision-making.

Abstract

End-to-end autonomous driving planners typically generate trajectories from current observations alone. However, real-world driving is highly dynamic, and such reactive planning cannot anticipate future scene evolution, often leading to myopic decisions and safety-critical failures. We propose ProDrive, a world-model-based proactive planning framework that enables ego-environment co-evolution for autonomous driving. ProDrive jointly trains a query-centric trajectory planner and a bird's-eye-view (BEV) world model end-to-end: the planner generates diverse candidate trajectories and planning-aware ego tokens, while the world model predicts future scene evolution conditioned on them. By injecting planner features into the world model and evaluating all candidates in parallel, ProDrive preserves end-to-end gradient flow and allows future outcome assessment to directly shape planning. This bidirectional coupling enables proactive planning beyond current-observation-driven decision-making. Experiments on NAVSIM v1 show that ProDrive outperforms strong baselines in both safety and planning efficiency, while ablations validate the effectiveness of the proposed ego-environment coupling design.