Build Autonomous Vehicles (AVs) in
Virtual Environments
Accelerate AV development with simulation and synthetic data generation (SDG) pipelines powered by advanced NVIDIA models, tools, and libraries. These include:
NVIDIA Cosmos™ world foundation models
Open-Source Simulation
Cosmos Predict
NVIDIA Cosmos Predict can be post‑trained on AV data to generate single and multiview videos for simulation, accelerating scenario creation and coverage for downstream training and testing.
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.
Omniverse NuRec
NVIDIA Omniverse Nurec
reconstructs high‑fidelity 3D worlds from real‑world multi‑sensor driving data and renders new sensor views and trajectories for replay, validation, and synthetic data generation.
AlpaSim
NVIDIA AlpaSim is an open source AV simulation framework that combines Omniverse NuRec scenes, configurable traffic and policy models, and scalable closed‑loop testing to iterate AV stacks over millions of virtual miles.
Cosmos Evaluator
NVIDIA Cosmos Evaluator is an automated scoring system that validates synthetic video quality across hallucinations, object correspondence, environment conditions, and attributes — at scale.
Fixer
NVIDIA Fixer is a one-step diffusion model that cleans up artifacts in rendered 3D views, boosting NeRF and 3D Gaussian splat reconstruction quality.
Asset Harvester
NVIDIA Asset Harvester is an end-to-end image-to-3D system that turns sparse, in-the-wild views of road users from driving logs into high-fidelity Gaussian-splat 3D assets ready for NuRec simulation pipelines in seconds.
Omniverse NuRec and Cosmos Transfer on CARLA
The leading open source AV simulator integrates NVIDIA Omniverse NuRec neural reconstruction and NVIDIA Cosmos Transfer for scalable synthetic data generation in its latest release.
Autonomous Vehicle Simulation Learning Resources
Accelerate AV Simulation With Neural Reconstruction and World 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.
Simulate and Scale Real-World AV Data With NuRec and Cosmos on CARLA
Deep dive into the latest open-source CARLA 0.9.16 release, and learn how to use AV simulation pipelines with NuRec and Cosmos Transfer. This session covers neural reconstruction and rendering workflows to bring real-world sensor data into simulation.
Enhance 3D Gaussian Reconstruction Quality for AV Simulation Using NuRec Fixer
Learn how to use NuRec Fixer to transform noisy 3D scenes into a crisp, artifact-free environment ready for AV simulation.