carla
Open-source simulator for autonomous driving research.
What is carla?
Open-source simulator for autonomous driving research.
Overview of carla
What it is
CARLA is an open-source simulator for autonomous driving research. It supports development, training, and validation of autonomous driving systems. It provides open digital assets including urban layouts, buildings, and vehicles. The simulation platform supports flexible specification of sensor suites and environmental conditions. This is the development branch ue58-dev for Unreal Engine 5.8.
Key features
- Open-source simulator for autonomous driving research.
- Provides open digital assets (urban layouts, buildings, vehicles).
- Supports flexible sensor suites and environmental conditions.
- Built on Unreal Engine 5.8 (ue58-dev branch).
- Includes Python API for scripting and control.
- Part of a larger ecosystem with leaderboard, scenario runner, ROS bridge, etc.
Use cases
- Development, training, and validation of autonomous driving systems.
- Research in autonomous driving, including perception, planning, and control.
- Benchmarking and leaderboard evaluation of autonomous driving stacks.
- Simulation for reinforcement learning and imitation learning.
- Integration with ROS and other autonomous driving frameworks.
Getting started
Clone the repository and run the setup script. See the repository README for detailed instructions.
git clone -b ue58-dev https://github.com/carla-simulator/carla.git CarlaUE5
cd CarlaUE5
./CarlaSetup.sh --interactive # Linux
### or CarlaSetup.bat on Windows
License and pricing
CARLA specific code is distributed under the MIT License. CARLA specific assets are distributed under the CC-BY License. The software is open-source and free to use.
Based on the project's public README and repository metadata.