GitHub repository
Open-source simulator for drones and autonomous vehicles built on Unreal Engine and Unity, designed for AI research.
What is GitHub repository?
AirSim is an open-source simulator for autonomous vehicles, including drones and cars, built on Unreal Engine and Unity. It provides a high-fidelity environment for AI research, enabling developers to test and validate autonomy algorithms in a physically and visually realistic simulation before real-world deployment. The simulator supports software-in-the-loop and hardware-in-the-loop integration with flight controllers like PX4 and ArduPilot.
Researchers and developers working on autonomous systems, AI, computer vision, and robotics, particularly those focused on aerial or ground vehicle autonomy who need a realistic simulation environment for algorithm development and testing.
AirSim offers a cross-platform, extensible simulation platform with rich APIs for programmatic control, making it ideal for AI research and experimentation. Its support for multiple game engines and integration with popular flight controllers provides flexibility and realism not found in many other open-source simulators.
Overview
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
Use Cases
Best For
- Testing autonomous drone navigation algorithms in a simulated environment
- Developing and validating computer vision models for vehicle perception
- Training reinforcement learning agents for autonomous driving scenarios
- Conducting hardware-in-the-loop simulations with PX4 or ArduPilot flight controllers
- Generating synthetic training data for deep learning applications
- Researching AI algorithms for aerial mobility and autonomous systems
Not Ideal For
- Projects requiring long-term support, bug fixes, or future feature updates
- Teams needing a simple, standalone simulator without Unreal Engine or Unity dependencies
- Organizations seeking commercial licensing, warranties, or enterprise-grade technical support
- New initiatives where migration to the commercial Project AirSim might be necessary soon
Pros & Cons
Pros
Built on Unreal Engine and Unity, AirSim provides physically and visually realistic simulations for drones and cars, as demonstrated in the detailed demo videos and weather effects.
Offers programmatic control via APIs in C++, Python, C#, and Java, enabling flexible data retrieval and vehicle manipulation for AI research, as outlined in the documentation.
Integrates with popular flight controllers like PX4 and ArduPilot for software-in-the-loop and hardware-in-loop simulations, allowing realistic testing with actual hardware.
Designed specifically for deep learning, with features like Computer Vision mode for image capture and APIs for generating synthetic training data, as highlighted in the research goals.
Cons
The repository is being archived with no further updates, as announced, making it unsuitable for projects needing ongoing bug fixes, security patches, or new features.
Requires building or integrating with Unreal Engine or Unity, which involves non-trivial steps and dependencies, as indicated in the platform-specific build instructions.
With the shift to the commercial Project AirSim, community contributions, third-party tools, and documentation updates are likely to decline, reducing long-term viability.
Frequently Asked Questions
Related Projects
GitHub repositoryOpen-source simulator for autonomous driving research.
WebotsWebots Robot Simulator
DrakeModel-based design and verification for robotics.
sumoEclipse SUMO is an open source, highly portable, microscopic and continuous traffic simulation package designed to handle large networks. It allows for intermodal simulation including pedestrians and comes with a large set of tools for scenario creation.
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.