Four examples of flight simulations on screen. These include a drone in flying over mountainous train, flying in close proximity to a tree and over the ocean. joins Microsoft’s Project AirSim early access program

Simulation has always been at the core of our development of autonomous drone software – an approach borne out of years of experience developing, testing and implementing cutting-edge mission critical technology for the America’s Cup, Formula 1 and hedge funds. Simulation allows us to test our code and train teams before drones controlled by our software take flight in the real world; it’s key to our maintaining the strict safety standards that are the hallmark of the aviation industry.

From the beginning, our simulation software of choice has been Microsoft’s AirSim – an experimental open source code base that has provided a common way for unmanned aerial vehicle developers to share research code and test new ideas around aerial AI development and simulation. Using AirSim, we have simulated BVLOS drone flights to inspect assets in challenging environments such as electricity pylons, oil rigs and wind turbines.

Building on insights gained from the first iteration of AirSim, Microsoft recently announced the launch of a commercial product called Project AirSim, an AI-first platform for safely developing and testing aerial autonomy through simulation, and has invited to join the Project AirSim early access program.

“We are pleased to have in the Project AirSim early access program. This collaboration enables us to tackle complex challenges involved in autonomous inspections and BVLOS operations” said Ade Famoti, Project AirSim Senior Director Strategic Partnerships & GTM, at Microsoft.

“Project AirSim offers developers a unique opportunity to use a scalable system that ensures their models can meet real-world challenges,” said Ganesh Rao, Project AirSim General Manager. “It brings together the power of cloud and AI at a flexible scale, pre-built environments, foundational pre-trained AI models, and the creation of new simulation capabilities in combination with existing ones to generate AI-ready data and build custom machine learning models.”

No doubt Project AirSim will continue to be an excellent resource for our engineering and commercial teams, noted Richard Hopkirk, our VP Engineering:

“If we are to realise our goal of building one of the leading operating systems for unmanned flight globally, we need to convince regulators and customers that BVLOS drone operations in unsegregated airspace can be conducted safely, each time, every time.

“In order to execute our drone operations perfectly in live trials, we need to be confident before we take to the air that our software is functioning correctly. Project AirSim is invaluable because it allows us to test our code, rehearse future operations and train our teams in a realistic, virtualised world. It’s proving brilliant for demonstrating our technology to prospective clients too, so our commercial team love it.”

About Microsoft Project AirSim

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 take off to cruising to landing. It also offers 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.