Search papers, labs, and topics across Lattice.
DriveDreamer-Policy is introduced as a unified driving world-action model that combines depth generation, future video generation, and motion planning. It uses a large language model to process language instructions, multi-view images, and actions, and then employs lightweight generators to produce depth, future video, and actions. Experiments on Navsim v1 and v2 show that DriveDreamer-Policy outperforms existing world-model-based approaches in closed-loop planning and world generation, achieving 89.2 PDMS and 88.7 EPDMS, respectively.
Explicitly modeling depth in world-action models significantly boosts planning robustness and future prediction quality for autonomous driving.
Recently, world-action models (WAM) have emerged to bridge vision-language-action (VLA) models and world models, unifying their reasoning and instruction-following capabilities and spatio-temporal world modeling. However, existing WAM approaches often focus on modeling 2D appearance or latent representations, with limited geometric grounding-an essential element for embodied systems operating in the physical world. We present DriveDreamer-Policy, a unified driving world-action model that integrates depth generation, future video generation, and motion planning within a single modular architecture. The model employs a large language model to process language instructions, multi-view images, and actions, followed by three lightweight generators that produce depth, future video, and actions. By learning a geometry-aware world representation and using it to guide both future prediction and planning within a unified framework, the proposed model produces more coherent imagined futures and more informed driving actions, while maintaining modularity and controllable latency. Experiments on the Navsim v1 and v2 benchmarks demonstrate that DriveDreamer-Policy achieves strong performance on both closed-loop planning and world generation tasks. In particular, our model reaches 89.2 PDMS on Navsim v1 and 88.7 EPDMS on Navsim v2, outperforming existing world-model-based approaches while producing higher-quality future video and depth predictions. Ablation studies further show that explicit depth learning provides complementary benefits to video imagination and improves planning robustness.
