DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving

TL;DR

DynFlowDrive introduces a flow-based latent world model for autonomous driving that predicts scene evolution under different actions, improving planning reliability without extra inference costs.

Contribution

It proposes a novel flow-based world modeling approach with a stability-aware trajectory selection for better autonomous driving planning.

Findings

Consistent performance improvements on nuScenes and NavSim benchmarks.

No additional inference overhead introduced by the method.

Effective modeling of scene transitions under various driving actions.

Abstract

Recently, world models have been incorporated into the autonomous driving systems to improve the planning reliability. Existing approaches typically predict future states through appearance generation or deterministic regression, which limits their ability to capture trajectory-conditioned scene evolution and leads to unreliable action planning. To address this, we propose DynFlowDrive, a latent world model that leverages flow-based dynamics to model the transition of world states under different driving actions. By adopting the rectifiedflow formulation, the model learns a velocity field that describes how the scene state changes under different driving actions, enabling progressive prediction of future latent states. Building upon this, we further introduce a stability-aware multi-mode trajectory selection strategy that evaluates candidate trajectories according to the stability of the induced scene transitions. Extensive experiments on the nuScenes and NavSim benchmarks demonstrate consistent improvements across diverse driving frameworks without introducing additional inference overhead. Source code will be abaliable at https://github.com/xiaolul2/DynFlowDrive.