microsoft/AirSim
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
This simulator helps AI researchers and developers test autonomous vehicle algorithms for drones and cars in realistic virtual environments. You can feed your AI models into the simulator and observe how the vehicles respond, generating data for further training. It's designed for those developing AI for self-driving cars, drone delivery, or other aerial and ground autonomous systems.
18,015 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to safely develop, test, and gather training data for deep learning, computer vision, or reinforcement learning algorithms for autonomous vehicles.
Not ideal if you are looking for a commercial-grade, fully supported platform, as this project is being archived in favor of a new product.
Stars
18,015
Forks
4,857
Language
C++
License
—
Category
Last pushed
May 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/microsoft/AirSim"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
lgsvl/simulator
A ROS/ROS2 Multi-robot Simulator for Autonomous Vehicles
microsoft/AirSim-NeurIPS2019-Drone-Racing
Drone Racing @ NeurIPS 2019, built on Microsoft AirSim
DeepTecher/AutonomousVehiclePaper
无人驾驶相关论文速递
learn-to-race/l2r
Open-source reinforcement learning environment for autonomous racing — featured as a conference...
salesforce/warp-drive
Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning Framework on a GPU (JMLR 2022)