microsoft /AirSim
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
★ 18,614⑂ 4,930👁 571⑃ 976● 3,414▤ 30
+1
日增长
18,614
stars
4,930
forks
571
watchers
976
prs
3,414
issues
30
releases
README
Welcome to AirSim AirSim is a simulator for drones, cars and more, built on Unreal Engine (we now also have an experimental Unity release). It is open-source, cross platform, and supports software-in-the-loop simulation with popular flight controllers such as PX4 & ArduPilot and hardware-in-loop with PX4 for physically and visually realistic simulations. It is developed as an Unreal plugin that can simply be dropped into any Unreal environment. Similarly, we have an experimental release for a Unity plugin. AirSim was conceived and created by Shital Shah with PX4 and hardware-in-loop code contributed by Chris Lovett. Our goal is to develop AirSim as a platform for AI research to experiment with deep learning, computer vision and reinforcement learning algorithms for autonomous vehicles. For this purpose, AirSim also exposes APIs to retrieve data and control vehicles in a platform independent way. Check out the quick 1.5 minute demo Drones in AirSim Cars in AirSim How to Get It Windows Download binaries Build it Linux Download binaries Build it macOS Build it For more details, see the use precompiled binaries document. How to Use It Documentation View our detailed documentation on all aspects of AirSim. Manual drive If you have remote control (RC) as shown below, you can manually control the drone in the simulator. For cars, you can use arrow keys to drive manually. More details !record screenshot !record screenshot Programmatic control AirSim exposes APIs so you can interact with the vehicle in the simulation programmatically. You can use these APIs to retrieve images, get state, control the vehicle and so on. The APIs are exposed through the RPC, and are accessible via a variety of languages, including C++, Python, C and Java. These APIs are also available as part of a separate, independent cross-platform library, so you can deploy them on a companion computer on your vehicle. This way you can write and test your code in the simulator, and later execute it on the real vehicles. Transfer learning and related research is one of our focus areas. Note that you can use SimMode setting to specify the default vehicle or the new ComputerVision mode so you don't get prompted each time you start AirSim. More details Gathering training data There are two ways you can generate training data from AirSim for deep learning. The easiest way is to simply press the record button in the lower right corner. This will start writing pose and images for each frame. The data logging code is pretty simple and you can modify it to your heart's content. !record screenshot A better way to generate training data exactly the way you want is by accessing the APIs. This allows you to be in full control of how, what, where and when you want to log data. Computer Vision mode Yet another way to use AirSim is the so-called "Computer Vision" mode. In this m
Top issues
#2955Fixed Wing Aircraft125 comments · 2020-08-20#2369Running SLAM system on AirSim44 comments · 2020-01-08#506Can I use a car and a multirotor at the same time?42 comments · 2017-10-02#4535Cannot open Blocks.uproject with UE4.2729 comments · 2022-05-20#2786IMU through MAVROS19 comments · 2020-06-21#1708Could not initialize SDL: XRandR support is required but not available19 comments · 2019-01-15#4524PX4 HITL + External Offboard Controller + AirSim17 comments · 2022-05-16#1567can't run the released binary version under linux17 comments · 2018-11-24
Discussions
#9840License for videos recorded from AirSim environments0 comments · 2026-09-18#9838Independent technical support for existing Microsoft AirSim workflows0 comments · 2026-08-26#9770Generating files for Blocks.uproject1 comments · 2026-04-16#9769lshaz: a possibly useful static optimization analysis tool?0 comments · 2026-03-24#5073Small-Object Detection of Human Footprints in Aerial Imagery Using YOLOv80 comments · 2026-02-28#5068Benign and Malicious0 comments · 2026-02-05#5060Installing AirSim on external storage0 comments · 2025-12-12#5055使用build.cmd时报错C:\Users\28382\Airsim-sjt\AirSim\AirLib\include\common\VectorMath.hpp(14,10): error C1083: 无法打开包括文件: “Eigen/Dense”: No such file or directory [C:\Users\28382\Airsim-sjt\AirSim\AirLib\AirLib.vcxproj0 comments · 2025-10-14
Latest release
v1.8.1 - Windows v1.8.1-windows 2022-07-18What's new Microsoft and IAMAI collaborated to advance high-fidelity autonomy simulations through Project AirSim—the evolution of AirSim— released under the MIT license as part of a DARPA-supported initiative. IAMAI is proud to have contributed to these efforts and has published its version of the Project AirSim repository at github.com/iamaisim/ProjectAirSim. Environments There are the following environments available: 1. AbandonedPark 1. Africa (uneven terrain and animated animals) 1. AirSimNH (small urban neighborhood block) 1. Blocks 1. Building_99 1. CityEnviron 1. Coast