What it does
CARLA is an open-source simulator for self-driving car research. It provides virtual cities with streets, buildings and vehicles where autonomous-driving software can be developed, trained and tested without putting anyone at risk.
Researchers can choose which sensors a virtual car carries and change the environmental conditions. Related projects include a leaderboard for comparing driving systems, a traffic-scenario runner and a bridge to ROS, a common robotics toolkit. The city layouts, buildings and vehicles are free to use.
This version is built on Unreal Engine 5 and needs a powerful computer with a high-end graphics card.
Who it's for
Researchers, students and engineers working on autonomous driving.
Can I use it without coding?
Developers only. Has to be built from source with Unreal Engine on a powerful machine. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Linux, Windows
- Computer
- Works best on a powerful computer or one with a graphics card (GPU)
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (MIT): Very permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- CARLA: An Open Urban Driving SimulatorResearch paper · Nov 2017
- Show HN: Fast Monte Carlo Permutation Simulator in CHacker News · Dec 2013