Avionics Digital Edition

Artificial Intelligence and Machine Learning Advancing in Aviation

The AI and ML issue of Avionics International.

Over the last year, several major flight demonstrations, research initiatives, and new deployments of artificial intelligence (AI) and machine learning (ML) applications quietly occurred and advanced as most of the aviation industry focused on grappling with the COVID-19 pandemic.

California-based startup Reliable Robotics, for example, in February demonstrated its ability to remotely pilot a modified Cessna 208 Caravan 50 miles away from where the flight occurred. In June of last year, Airbus completed a two-year effort, the Autonomous Taxi, Take-Off and Landing (ATTOL) project, that featured two world-firsts for the aviation industry: fully automatic vision-based takeoffs and landings, controlled using onboard image recognition technology.

Some major recent demonstrations of artificial intelligence by the U.S. military also serve as a status update on where the adoption of the technology is today. In what the U.S. Air Force said was the first time artificial intelligence has commanded a military system, an AI algorithm helped to steer the radar of a Lockheed Martin U-2 reconnaissance aircraft and navigate the plane in a Dec. 15 flight from Beale Air Force Base in California.

As our online December coverage of the demonstration at the time mentions, the Air Combat Command’s (ACC) U-2 Federal Laboratory researchers at Beale AFB developed the ARTUµ AI algorithm and trained it to execute specific in-flight tasks that otherwise would have been performed by a human U-2 pilot.

During the Dec. 15 flight, a reconnaissance mission for a simulated missile strike, the ARTUµ algorithm helped navigate the aircraft and used its radar system to scan the area for enemy missile launchers.

These are among the reasons why we decided to dedicate this issue to near-term AI and ML applications for aviation, coupled with what’s being researched and developed for the future. In this issue, Xwing CTO Maxime Gariel provides an update on how their internally developed technology also enables remote piloting of a Grand Caravan.

We also caught up with the engineer who led the development of CMC Electronics’ first civil certified avionics multicore computer to learn how they achieved an avionics industry first. Elsewhere an overview is provided of the type of AI algorithm for flight schedule-driven airline fleet maintenance planning being developed at an applied science institute in the Netherlands.

Kelsey Reichmann covers the expanding adoption of AI and ML by the growing commercial unmanned aircraft systems industry, and Frank Wolfe talks to Lockheed Martin Skunk Works, General Atomics, and BAE Systems to discover how AI and ML will unlock new multi-aircraft collaboration, precision targeting, and fully autonomous operations in denied communications environments for military jets.

Tell us what we missed with an email to wbellamy@accessintel.com and we’ll see that it gets covered in an upcoming issue or online article, thanks for reading!