Build Autonomous Vehicles in Virtual Environments
Accelerate AV development with simulation and synthetic data generation (SDG) pipelines powered by NVIDIA’s advanced models, tools, and libraries. These include:
NVIDIA Cosmos world foundation models for post-training and data generation
NVIDIA NuRec for neural reconstruction
Synthetic datasets to kickstart AV workflows

Open-Source Autonomous Vehicle Simulation Tools and Technologies
NVIDIA Cosmos Transfer
Discover faster and superior photorealistic world generation from text prompts and multiple spatial control inputs derived from real-world driving data or simulation.
NVIDIA NuRec and Cosmos Transfer on CARLA
The leading open-source AV simulator is integrating NVIDIA NuRec neural reconstruction and Cosmos Transfer for scalable synthetic data generation in its latest release.
NVIDIA Cosmos Predict2
With improved speed, scalability, and flexibility, Cosmos Predict2 can be post-trained on AV data to generate single and multiview videos for accelerated development.
NVIDIA Physical AI Dataset
Check out open-source synthetic data for AV training, including Cosmos-generated videos and a starter pack of scenes for neural reconstruction.
Autonomous Vehicle Simulation Learning Resources
Accelerate AV Simulation With Neural Reconstruction and World Foundation Models
In this tech blog, we highlight the latest NVIDIA APIs, Cosmos world foundation models, and NVIDIA NIM™ microservices to help you kickstart your data pipelines.
Simplify End-to-End AV Development With New NVIDIA Cosmos Transfer NIM
This blog showcases how you can create world models and generate synthetic data (SDG) to accelerate end-to-end AV training, as well as closed-loop training and in-vehicle inference.
Advancing AV Development With Sensor Simulation and NVIDIA Cosmos
This session features the workflows developed by NVIDIA AV simulation ecosystem partners for scenario creation, SDG, 3D reconstruction, and closed-loop simulation.
Reconstruct Real-World Environments Using NVIDIA Omniverse NuRec
Learn how to accelerate AV development using NuRec, a set of APIs and libraries that generates neural simulation data from real-world data.