C++ C# C Python Shell CMake Batchfile
Permalink
Failed to load latest commit information.
AirLib Added virtual destructors (warnings from UE 4.17) Oct 19, 2017
AirLibUnitTests API refactor, simSetPose, simGetPose, reset for drones Oct 15, 2017
DroneServer API refactor, simSetPose, simGetPose, reset for drones Oct 15, 2017
DroneShell Clang compile issues Oct 7, 2017
Examples simSetPose, simGetPose enhancements, add more cameras to quadrotor Oct 6, 2017
HelloCar numpy example, docs update PythonClient->AirSimClient rename, reset API Oct 4, 2017
HelloDrone added perspective depth Sep 30, 2017
LogViewer Fix LogViewer for other cultures. Jun 5, 2017
MavLinkCom API refactor, simSetPose, simGetPose, reset for drones Oct 15, 2017
PythonClient Merge pull request #544 from ShreyasSkandan/patch-1 Oct 19, 2017
Unreal rollback widget asset to 4.16 version Oct 21, 2017
cmake API refactor, simSetPose, simGetPose, reset for drones Oct 15, 2017
docs docs update for Git issues Oct 19, 2017
external Fix invalid Pythin Env issue, update rpclib to latest Oct 10, 2017
tools Fix windows clean build (installs cmake if we need it). Apr 24, 2017
.gitignore Some fixes and enhancements for #540 Oct 19, 2017
.gitmodules added rpclib submodule Feb 24, 2017
.travis.yml clang compile error fix, remove OSX from travis Sep 28, 2017
AirSim.sln numpy example, docs update PythonClient->AirSimClient rename, reset API Oct 4, 2017
LICENSE readme and license update Feb 15, 2017
README.md protect against bad settings file (#485), other minor updates(#484, 477 Sep 29, 2017
UnrealPluginFiles.vcxproj API refactor, simSetPose, simGetPose, reset for drones Oct 15, 2017
UnrealPluginFiles.vcxproj.filters API refactor, simSetPose, simGetPose, reset for drones Oct 15, 2017
build.cmd enable SUV model download Oct 21, 2017
build.sh osx clang 3.9 setup Sep 4, 2017
clean.cmd require reset() as first call, checks for reset(), update() seq Aug 1, 2017
clean.sh fixed pushd issue in setup.sh, cmake issue with -L Jul 21, 2017
install_run_all.sh switch to UE 4.17, joystick code for Linux Aug 16, 2017
setup.sh enable SUV model download Oct 21, 2017

README.md

Welcome to AirSim

AirSim is a simulator for drones, cars and more built on Unreal Engine. It is open-source, cross platform and supports hardware-in-loop with popular flight controllers such as PX4 for physically and visually realistic simulations. It is developed as an Unreal plugin that can simply be dropped in to any Unreal environment you want.

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

AirSim Demo Video

What's New

  • We now have the car model.
  • New built-in flight controller called simple_flight that "just works" without any additional setup. It is also now default.
  • AirSim now also generates depth as well as disparity impages that is in camera plan.
  • We also have official Linux build now! If you have been using AirSim with PX4, you might want to read the release notes.
  • No need to build the code. Just download our binaries and you are good to go!

How to Get It

Windows

Linux

How to Use It

Chosing Your Vehicle: Car or Multirotor

By default AirSim spawns multirotor. You can easily change this to car and use all of AirSim goodies. Please see using car guide.

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

Programmatic control

AirSim exposes APIs so you can interact with 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 RPC and accessible via variety of languages including C++, Python, C# and Java.

These APIs are also available as a part of a separate independent cross-platform library so you can deploy them on an companion computer on your vehicle. This way you can write and test your code in simulator and later execute it on the real vehicles. Transfer learning and related research is one of our focus areas.

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 on 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 desire.

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 so-called "Computer Vision" mode. In this mode, you don't have vehicle physics and dynamics but you can use keyboard to move around and use APIs to position the vehicle in any arbitrary pose and get images such as depth, disparity, surface normals or object segmentation.

More details

Video Tutorials

Participate

Paper

More technical details are available in AirSim paper (FSR 2017 Conference). Please cite this as:

@inproceedings{airsim2017fsr,
  author = {Shital Shah and Debadeepta Dey and Chris Lovett and Ashish Kapoor},
  title = {AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles},
  year = {2017},
  booktitle = {Field and Service Robotics},
  eprint = {arXiv:1705.05065},
  url = {https://arxiv.org/abs/1705.05065}
}

Contribute

We welcome contributions to help advance research frontiers.

Contact

Join the AirSim group at Facebook to stay up to date or ask any questions.

FAQ

If you run into problems, check the FAQ and feel free to post issues on the AirSim github.

License

This project is released under MIT License. Please review License file for more details.