Highlights –

  • Utilizing 3D simulation, Project AirSim, like the original AirSim, uses AI models to design, develop, and test drones and other autonomous aircraft.
  • Project AirSim helped Airtonomy train drones to cope with extreme weather conditions like snow, rain, strong winds, and high temperatures.

A simulator for drones, cars, and other autonomous vehicles, AirSim was an open-sourced program provided by Microsoft Research several years ago. After years of experimentation, Microsoft eventually decided to archive the repository for the original AirSim platform. However, on July 18, 2022, it introduced “Project AirSim,” a new AirSim simulation platform for the aerospace sector.

Like the original AirSim, Project AirSim uses AI models to design, develop, and test drones and other autonomous aircraft utilizing 3D simulation. According to officials, “strong experience in coding and machine learning” was a need for the previous AirSim, which is one of the main differences between it and the new Project AirSim. (The company’s Bonsai machine-teaching technology and reinforcement learning from Azure Machine Learning Services were combined with the original AirSim.)

About Project AirSim

According to the Microsoft, Project AirSim leverages Azure to collect “huge volumes of data for training AI models on exactly which actions to take at each phase of flight, from takeoff to cruising to landing.” The program will offer libraries of simulated 3D settings.

According to Microsoft officials, project AirSim could be used for various purposes, from passenger planes to hobbyist drones. Autonomous aircraft can be used to carry packages, examine machinery, and more.

The platform can use processing power from Microsoft Azure and data from Bing Maps and other vendors to build millions of intricate virtual 3-D settings. Customers can create their venues or select from a library of specific locations worldwide.

Gurdeep Pall, Microsoft corporate vice president for business incubations in technology and research, confirmed that the company is working towards figuring out how Project AirSim could help with autonomous flight systems certification with the help of civil aviation regulators.

Ashish Kapoor, who created the original AirSim, said, “Our ability to capture that data and translate it into autonomy is going to significantly change the landscape of aviation. And because of that, we are going to see many more vehicles in the sky, helping to monitor farms, inspect critical infrastructure, and transport goods and people to the remotest of places.”

The foundation of Microsoft’s Project AirSim is an earlier open-source program developed by Microsoft Research that requires a high level of coding and machine learning proficiency. The recently disclosed commercial platform will simplify the testing and training of AI-powered airplanes. Partners include Ansys and MathWorks, the two businesses that offer software for creating simulations based on AI.

Airtonomy, a North Dakota-based company, was one of the early-access users of this project. Project AirSim helped Airtonomy train drones to cope with extreme weather conditions like snow, rain, strong winds, and high temperatures. Another partner is Bell, which used this project to sharpen the ability of its drone to land autonomously.

The simulation platform is being made available in a limited preview after this week’s Farnborough International Airshow in Britain.

Experts’ Take

“Project AirSim is a critical tool that lets us bridge the world of bits and the world of atoms, and it shows the power of the industrial metaverse — the virtual worlds where businesses will build, test and hone solutions, and then bring them into the real world,” Gurdeep Pall said.

Matt Holvey, Bell’s director of intelligent systems, said, “AirSim allowed us to get a true understanding of what to expect before we flew in the real world. It’s going to be one of the tools that will accelerate the timeline for scaling aerial mobility. If we have to test and validate everything by hand, or in a physical lab, or on a flying aircraft, we’re talking about decades, and it’s going to cost billions. But Project AirSim pulls that forward through high-fidelity simulation.”