# carla-simulator/carla

Open-source simulator for autonomous driving research.

Repository: https://github.com/carla-simulator/carla
Canonical: https://ross.abutalabs.com/products/carla
Homepage: http://carla.org
Language: C++
License: MIT
License Family: permissive
Topics: simulator, autonomous-vehicles, autonomous-driving, research, ai, artificial-intelligence, computer-vision, deep-learning, deep-reinforcement-learning, imitation-learning, self-driving-car, ue4, unreal-engine-4, cross-platform, carla, carla-simulator, ros
Last push: 2026-08-26T16:31:20+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 16, longevity 100
- inputs: {"age_days": 3235, "days_push": 7, "days_rel": 351, "gap_med": 270, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14328, forks 4670 (observed 2026-08-28T04:11:06.756190+00:00)

## What it is
CARLA is an open-source simulator for autonomous driving research built on Unreal Engine, providing open digital assets like urban layouts, buildings, and vehicles. It supports development, training, and validation of autonomous driving systems with configurable sensor suites, environmental conditions, and a flexible Python API.

## Use cases
- simulate autonomous driving scenarios for research
- train reinforcement learning agents for self-driving cars
- test perception models with simulated LIDAR and camera data
- validate autonomous driving stacks on a benchmark leaderboard
- generate synthetic sensor data for computer vision
- run traffic scenario simulations with ScenarioRunner
- integrate a driving simulator with ROS

## When to choose
- you need a high-fidelity driving simulator with open assets and sensor simulation
- you want to train or validate autonomous driving agents with LIDAR, cameras, GPS, and weather control
- you need ROS integration or multi-client server architecture for distributed simulation
- you want fast non-rendered simulation for planning and control research

## When to avoid
- you need a lightweight simulator that runs on modest hardware (CARLA requires a high-end GPU and 32+ GB RAM)
- you need general-purpose robotics simulation beyond driving (consider Gazebo or Isaac Sim)
- you need game development tooling rather than a research simulation platform
- you require older OS support like Ubuntu 20.04 or Windows 10 for the UE5 version

## Facets
- artifact type: application
- maturity: active
- function: simulation, machine-learning, computer-vision, deep-learning, reinforcement-learning, robotics
- domain: autonomous-vehicles, simulation, robotics, artificial-intelligence, computer-vision, deep-learning
- platform: windows, cpp, python, cross-platform
- tags: autonomous-driving, unreal-engine, sensor-simulation, lidar, ros, self-driving-car, open-source-assets, driving-benchmark, research, linux, gpu

## Member repositories
- carla-simulator/carla (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:06.756190+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:12:38.994010+00:00, confidence not recorded.
  - readme: https://github.com/carla-simulator/carla (fetched 2026-08-28T04:11:06.756190+00:00, sha f1a3086a7146)
  - homepage: http://carla.org (fetched 2026-08-29T08:06:08.555787+00:00, sha 852b5db0150f)
- Data as of 2026-08-30T08:39:29.467469+00:00.