Microsoft expands AI research project to self-driving vehicles

Microsoft is expanding its “AirSim” Artificial Intelligence (AI) research project to include car simulation which will help advance the research and development of self-driving vehicles.

Microsoft open-sourced "AirSim" earlier this year, which is a high-fidelity system, for testing the safety of artificial intelligence systems.

"AirSim comes with a detailed 3D urban environment that includes a variety of diverse conditions, including traffic lights, parks, lakes and construction sites. Users can test their systems in several types of neighborhoods, including downtown, semi-urban, vegetation and industrial environments," Microsoft writes in its blog post.

AirSim has been developed as a plugin for "Unreal Engine", a popular tool for game development. It means that the car simulation is decoupled from the environment it runs in. "You can create an environment for your specific needs, such as a city or rural road, or choose from a variety of environments available online, and then simply drop in the AirSim plugin to test your self-driving algorithms in that environment," says Shital Shah, Principal Research Software Engineer at Microsoft.

AirSim extensibility also allows researchers and developers to incorporate new sensors, vehicles or even use different physics engines. In future releases, Microsoft aims to add new sensors, better vehicle physics, weather modeling and even more detailed realistic environments.