Microsoft revamps its Project AirSim for easier autonomous aircraft simulation training

Kareem Anderson


Microsoft is dusting the mothballs off its open-source drone project from years back and relaunching it as Project AirSim today to help build, test, and train aircraft through 3D simulation.

Today, July 18, 2022, Microsoft took the wraps off of Project AirSim, an end-end platform that will make use of 3D virtual environments derived by Bing Maps and other mapping technologies, all generated using Microsoft’s Azure cloud processing.

Microsoft’s Project AirSim is intended to help accelerate the learning curve for autonomous flight engineers and Advanced Ariel Mobility (AAM) customers by simplifying the original open-source effort that required extensive knowledge of coding and machine learning algorithms, and automating many of those processes in the background for users.

Per Microsoft’s press release today,

Project AirSim uses the power of Azure to generate massive amounts of data for training AI models on exactly which actions to take at each phase of flight, from takeoff to cruising to landing. It will also offer libraries of simulated 3D environments representing diverse urban and rural landscapes as well as a suite of sophisticated pretrained AI models to help accelerate autonomy in aerial infrastructure inspection, last-mile delivery and urban air mobility.

While Project AirSim was announced today in limited preview, Microsoft has been working with partners to test the platform for some time and racked up the likes of Airtonomy and Bell who used the project to help prepare NASA’s System Integration and Operationalization (SIO).

Microsoft sees “almost limitless” potential uses cases of AirSim and suggests those who are interested visit here for more information.