#6767th of 75 in ML frameworks and librariesFor research, robotics and education
airsim
Unreal Engine drone and car simulator for autonomous vehicle research
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 18.6k
- License
- custom license
- Last commit
- Sep 2026
- Last release
- Jul 2022
- Language
- C++
17,957 on 31 Mar 202618,563 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
AirSim is an Unreal Engine plugin, with an experimental Unity version, that simulates drones and cars. It supports software-in-the-loop with PX4 and ArduPilot, hardware-in-the-loop with PX4, and an RPC API for C++, Python, C# and Java to pull images and state and to control vehicles. It is aimed at deep learning, computer vision and reinforcement learning work.
Who it is for: Robotics and RL researchers testing drone or car autonomy in simulation
Strengths
- Integrates with PX4 and ArduPilot for software-in-the-loop, plus PX4 hardware-in-the-loop
- RPC API in C++, Python, C# and Java; client library can run on a companion computer
- Computer Vision mode returns depth, disparity, normals and segmentation without vehicle physics
- Built-in recording of pose and images, plus weather controls
Weaknesses
- Last release is 2022-07-18; the README points to a separate Project AirSim
- Requires Unreal Engine; the Unity release is described as experimental
- README lists no prebuilt binaries for macOS, only a build guide
- Hardware requirements are not stated in the README
What it needs
- Needs Unreal Engine, Unity (experimental), PX4, ArduPilot
Also in ML frameworks and libraries
See all 75| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd for deep learning | 94 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 92 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts | 91 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 90 out of 100 |