# microsoft/AirSim

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

Repository: https://github.com/microsoft/AirSim
Canonical: https://ross.abutalabs.com/products/airsim
Homepage: https://microsoft.github.io/AirSim/
Language: C++
License: NOASSERTION
License Family: other
Topics: drones, ai, self-driving-car, autonomous-vehicles, autonomous-quadcoptor, research, computer-vision, artificial-intelligence, deeplearning, deep-reinforcement-learning, control-systems, pixhawk, cross-platform, platform-independent, airsim, unreal-engine, simulator
Last push: 2026-06-30T19:34:07+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 90, release rhythm 8, longevity 100
- inputs: {"age_days": 3488, "days_push": 64, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 18424, forks 4916 (observed 2026-08-28T04:11:26.661842+00:00)

## What it is
AirSim is an open-source simulator for drones and cars built on Unreal Engine (with an experimental Unity plugin), developed by Microsoft Research for AI research. It provides physically and visually realistic simulation with software/hardware-in-the-loop support for PX4 and ArduPilot, plus cross-platform APIs to control vehicles and retrieve sensor data.

## Use cases
- simulate drones for reinforcement learning research
- test self-driving car algorithms in a virtual environment
- generate synthetic training images for computer vision
- software-in-the-loop simulation with PX4 or ArduPilot flight controllers
- control simulated vehicles programmatically via APIs
- experiment with deep learning for autonomous vehicles

## When to choose
- you need a physically and visually realistic drone or car simulator for AI research
- you want SIL/HIL integration with PX4 or ArduPilot
- you need cross-platform simulation with programmatic APIs for data collection

## When to avoid
- you need an actively maintained simulator - the repo is archived and no further updates are made
- you want a commercial-grade end-to-end aerial autonomy platform (consider Project AirSim instead)
- you need lightweight simulation without Unreal Engine dependencies

## Facets
- artifact type: library
- maturity: abandoned
- function: simulation, machine-learning, computer-vision, reinforcement-learning
- domain: simulation, autonomous-vehicles, robotics, artificial-intelligence
- platform: windows, cpp, cross-platform
- tags: unreal-engine, drones, simulator, self-driving-car, px4, unity, linux, macos

## Member repositories
- microsoft/AirSim (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:26.661842+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 2026-08-29T17:02:02.908678+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/AirSim (fetched 2026-08-28T04:11:26.661842+00:00, sha 3324c4fe8491)
  - homepage: https://microsoft.github.io/AirSim/ (fetched 2026-08-29T07:59:39.731350+00:00, sha a30c8a93fa95)
- Data as of 2026-08-30T08:39:29.467469+00:00.