Waymo published a summary of its simulation capabilities for autonomous vehicles with many example videos.
They cover many driving scenarios and outcomes with multi-sensor simulations derived from real-world data.
The model’s architecture offers high controllability, allowing our engineers to modify simulations with simple language prompts, driving inputs, and scene layouts. Notably, the Waymo World Model generates high-fidelity, multi-sensor outputs that include both camera and lidar data.
Through our specialized post-training, we are transferring that vast world knowledge from 2D video into 3D lidar outputs unique to Waymo’s hardware suite.
The Waymo World Model can generate virtually any scene—from regular, day-to-day driving to rare, long-tail scenarios—across multiple sensor modalities.