AirSim

{{Short description|Robotics simulator}}

{{Infobox software

| name = AirSim

| title = AirSim

| logo =

| logo caption =

| logo_size =

| logo_alt =

| screenshot =

| caption =

| screenshot_size =

| screenshot_alt =

| collapsible =

| author = Microsoft Research

| developer = Microsoft and community

| released = {{Start date and age|2017|02|16}}

| discontinued =

| latest release version = 1.8.1

| latest release date = {{Start date and age|2022|07|17}}{{cite web|url=https://github.com/microsoft/AirSim/tags|title=Tags · microsoft/AirSim · GitHub|website=GitHub AirSim repository|language=en|access-date=2022-07-20}}

| latest preview version =

| latest preview date =

| repo = {{URL|https://github.com/microsoft/AirSim}}

| programming language = C++

| operating system = Windows 10, macOS, Linux

| platform =

| size =

| language =

| language count =

| language footnote =

| genre = Flight simulator

| license = MIT License

| website = {{URL|https://microsoft.github.io/AirSim}}

}}

AirSim (Aerial Informatics and Robotics Simulation) is an open-source, cross platform simulator for drones, ground vehicles such as cars and various other objects, built on Epic Games’ proprietary Unreal Engine 4 as a platform for AI research.{{Cite web|url=http://www.digitaljournal.com/tech-and-science/technology/microsoft-ai-simulator-includes-autonomous-car-research/article/508552|title=Microsoft AI simulator includes autonomous car research|date=November 26, 2017|website=www.digitaljournal.com}} It is developed by Microsoft and can be used to experiment with deep learning, computer vision and reinforcement learning algorithms for autonomous vehicles.{{Cite web | url=https://github.com/microsoft/AirSim/blob/master/README.md | title=Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research: Microsoft/AirSim| website=GitHub| date=30 March 2020}}{{Cite web|url=https://www.infoq.com/news/2017/02/airsim/|title=Microsoft AirSim, a Simulator for Drones and Robots|website=InfoQ}} This allows testing of autonomous solutions without worrying about real-world damage.{{Cite news|url=https://www.bbc.com/news/technology-62202118|title=Microsoft launches simulator to train drone AI systems|author-first=Chris|author-last=Vallance|work=BBC News |date=18 July 2022 |access-date=20 July 2022}}

AirSim provides some 12 kilometers of roads with 20 city blocks and APIs to retrieve data and control vehicles in a platform independent way. The APIs are accessible via a variety of programming languages, including C++, C#, Python and Java. AirSim supports hardware-in-the-loop with driving wheels and flight controllers such as PX4 for physically and visually realistic simulations. The platform also supports common robotic platforms, such as Robot Operating System (ROS).{{cite web |title=Aerial Informatics and Robotics Platform |url=https://www.microsoft.com/en-us/research/project/aerial-informatics-robotics-platform/ |website=Microsoft Research}} It is developed as an Unreal plug-in that can be dropped into any Unreal environment.{{cite web |title=Aerial Autonomy: Project AirSim |url=https://www.microsoft.com/en-us/ai/autonomous-systems-project-airsim |website=Microsoft AI |language=en-us}} An experimental release for a Unity plug-in is also available.{{Cite web|url=https://blogs.unity3d.com/2018/11/14/airsim-on-unity-experiment-with-autonomous-vehicle-simulation/|title=AirSim on Unity: Experiment with autonomous vehicle simulation|date=November 14, 2018|website=blogs.unity3d.com}}{{Cite web|url=https://venturebeat.com/2018/11/14/microsofts-open-source-airsim-platform-comes-to-unity/|title=Microsoft's open source AirSim platform comes to Unity|date=November 14, 2018|website=VentureBeat}}

On December 15, 2023 Microsoft has shutdown the development of the project.https://www.businessinsider.com/microsoft-shutters-project-airsim-ai-strategy-openai-2023-10

See also

{{Portal|Free and open-source software}}

References

{{Reflist}}

Further reading

  • {{Cite arXiv|author1=Shital Shah |author2=Debadeepta Dey |author3=Chris Lovett |author4=Ashish Kapoor|title=AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles|date=2017-11-03|class=cs.RO |eprint=1705.05065 }}