DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving
This work addresses planning reliability for autonomous driving systems, representing an incremental improvement through a novel method for a known bottleneck.
The paper tackles the problem of unreliable action planning in autonomous driving by proposing DynFlowDrive, a flow-based dynamic world model that captures trajectory-conditioned scene evolution, resulting in consistent improvements on nuScenes and NavSim benchmarks without extra inference overhead.
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.