🚀 CARLA 0.9.16 Release: Digital Twins, ROS2, SimReady and Experimental Integrations with NVIDIA Cosmos Transfer and NuRec

We’re thrilled to share great news: a new release of CARLA is coming this summer! The new release will introduce powerful new tools and integrations designed to take realism, interoperability, and extensibility to the next level — helping researchers, developers, and engineers push the boundaries of autonomous systems and embodied AI.

Whether you’re building complex autonomy stacks, experimenting with digital twins, or exporting CARLA content to other platforms — this release brings you closer to production-grade simulation workflows.

Let’s dive in.

—

🧪NVIDIA Cosmos Transfer Support (Beta)

cosmos_transfer1

In this release, CARLA will feature experimental support for NVIDIA Cosmos — including integration with Transfer1, a foundational style transfer model designed to augment simulation outputs. With Transfer1, users can generate endless hyper-realistic video variations from CARLA sequences using simple prompts. This capability is ideal for:

Expanding visual diversity in perception datasets
Bridging the domain gap for sim-to-real training
Exploring edge cases with photorealistic textures, lighting, and weather

Furthermore, by using this feature in combination with Inverted AI DRIVE API, users can produce realistic behaviors enhanced with endless visual variations. The perfect combination for training AV stacks! You can read more about this topic here: NVIDIA: Acceleraging AV Simulation with Neural Reconstruction and World Foundational Models.

invertedai_transfer1

The CARLA Cosmos Transfer1 integration is in Beta — we welcome community feedback as we continue to develop it.

🎥 Neural Rendering with NVIDIA NuRec (Beta)

nurec

We’re also introducing experimental support for NVIDIA NuRec, a state-of-the-art neural rendering pipeline.

With this integration, CARLA scenes can be rendered using a learned representation of light and geometry — enabling:

Realistic rendering from arbitrary viewpoints
Faster replays and view synthesis
Neural graphics integration with synthetic datasets

This is a major step toward photorealistic simulation, especially for perception training and evaluation. Expect improvements over the next few releases as the neural rendering pipeline evolves.

📦 SimReady USD Exporter (Beta)

carla_to_simready

Need to export your CARLA environments or assets to other simulators or visualization platforms?

Our new USD SimReady Exporter lets you package your CARLA scenes and assets in the SimReady format — making them portable to the OpenUSD ecosystem and beyond.

Highlights:

Export environment geometry, materials, textures, and metadata to USD
Maintain physical properties and SimReady naming conventions
Ideal for digital twin reuse, simulation federation, and visualization in tools like Omniverse or Isaac Sim

Whether you’re simulating, rendering, or training agents across multiple platforms, this tool reduces friction and increases reusability. Thanks to the NVIDIA team for this contribution!

🗺️ Digital Twin Tool v2: Build Your World From OpenStreetMap

digital_twins

We’ve completely re-engineered the Digital Twin Tool to make it easier than ever to generate full environments from real-world data. Leveraging OpenStreetMap as the primary data source, this new version brings:

Automatic parsing of road networks, intersections, and topology
Heightmaps and semantic information from terrain datasets
Flexible parameterization for traffic furniture, props, and buildings
Templated urban layouts to fill in missing geometry while preserving georeference

With just a few clicks, users can generate a CARLA environment grounded in the real world — ideal for geo-specific experiments, regulatory testing, and sim-to-real pipelines. Now shipped as a standalone and easy-to-use tool.

This is a step toward bridging digital twins with procedural simulation. And it’s just the beginning.

🧭 Native ROS2 Support

ros2

We’ve heard you — ROS2 is here.

CARLA now ships with native ROS2 integration, opening the door for:

Out-of-the-box compatibility with modern robotic stacks
DDS-based message passing and time synchronization
Integration examples included

You can now connect CARLA to ROS2 Foxy, Galactic, Humble and more — with sensor streams, ego control, and world state all integrated into your ROS2 nodes.

Autonomy teams, rejoice.

🔧 How to Get Started

All the new features will be available on the latest branch. You’ll find updated documentation, new examples, and experimental flags to enable the NVIDIA integrations.

🧪 Experimental features are opt-in and require additional dependencies. Make sure to check the README before running.

🎯 What’s Next

We’re actively working on improving CARLA’s sensor stack, procedural environment generation, and interoperability with other simulators. If you’re interested in contributing, collaborating, or testing experimental tools — reach out on Discord, GitHub, or open an issue.

As always, CARLA is open-source and community-driven. Thank you to everyone who contributes, tests, reports bugs, and pushes the boundaries of what’s possible with simulation.

Happy simulating! 🛞

— The CARLA Team

← Previous Post