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.[2] It is developed by Microsoft and can be used to experiment with deep learning, computer vision and reinforcement learning algorithms for autonomous vehicles.[3][4] This allows testing of autonomous solutions without worrying about real-world damage.[5]

AirSim
Original author(s)Microsoft Research
Developer(s)Microsoft and community
Initial releaseFebruary 16, 2017 (2017-02-16)
Stable release
1.8.1 / July 17, 2022 (2022-07-17)[1]
Repositorygithub.com/microsoft/AirSim
Written inC++
Engine
  • Unreal Engine 4
Operating systemWindows 10, macOS, Linux
TypeFlight simulator
LicenseMIT License
Websitemicrosoft.github.io/AirSim

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).[6] It is developed as an Unreal plug-in that can be dropped into any Unreal environment.[7] An experimental release for a Unity plug-in is also available.[8][9]

See also

References

Further reading

  • Shital Shah; Debadeepta Dey; Chris Lovett; Ashish Kapoor (2017-11-03). "AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles". arXiv:1705.05065 [cs.RO].
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.