USAF C-17 demonstrates real time magnetic navigation

A Department of the Air Force-MIT Artificial Intelligence Accelerator team successfully demonstrated real time magnetic navigation. They flew three missions out of Edwards AFB during Golden Phoenix that ran from May 11-15. The team used a neural network, AI, and machine learning to calibrate the system on a commercial laptop while in flight. The team used data from around the world to build a library that helped remove noise generated by the aircraft, and then compare the position of the aircraft to known magnetic maps. Magnetic navigation systems will be effective for hypersonic glide vehicles, submarines, and aircraft.

CAMBRIDGE, Mass. (AFNS) --
In a groundbreaking achievement, the Department of the Air Force-Massachusetts Institute of Technology Artificial Intelligence Accelerator, or AIA, MagNav project recently performed real-time magnetic navigation, or MagNav, on the C-17A Globemaster III in flight, becoming the first organization to successfully demonstrate this cutting-edge technology in real-time on a Department of Defense aircraft.
MagNav equipment loaded on the back of a C-17A Globemaster III, ready for the first real-time demonstration on during Exercise Golden Phoenix May 11-15.
MagNav equipment is loaded on the back of a C-17A Globemaster III, ready for the first real-time demonstration on a Defense Department aircraft, during exercise Golden Phoenix, May 11-15, 2023. In the groundbreaking achievement, the Department of the Air Force-Massachusetts Institute of Technology Artificial Intelligence Accelerator MagNav project performed real-time magnetic navigation on the C-17A in flight, becoming the first organization to successfully demonstrate the cutting-edge technology in real-time.

The AIA MagNav team, in conjunction with personnel from MIT, MIT Lincoln Laboratory, the Air Force Research Laboratory Sensors Directorate and the Air Force Institute of Technology Autonomy and Navigation Center, flew three Travis Air Force Base, California, C-17 sorties to the test complex at Edwards AFB, California, during exercise Golden Phoenix, May 11-15.

The team harnessed the power of AI and machine learning through the AIA’s calibration and positioning neural network, which was trained during flight in a matter of minutes on a commercially-available laptop. The team leveraged transfer learning from AI models built on previously collected C-17 data, which significantly accelerated the neural network training process.

www.af.mil...

I do not know how accurate this system will end up being but this is great news. If GPS or whatever goes down this will be something I would guess an enemy can not jam. Amazing.

a reply to: 727Sky

We should get a report in the next couple months that will give details about how accurate it is, but I'd say at least as accurate as INS, without the long alignment times.

I wonder if mag nav is needed for hypersonic glide vehicles, a technology our enemies have already developed.

a reply to: IndieA

No. It's just another way that they can navigate, but it isn't required for anything. And "already developed" is a bit of a stretch. There's a world of difference between "operational" and "effective".

a reply to: Zaphod58

MagNav would be great for times when an enemy jams GPS signals. Be cool to see if some of the AI chips in smart phones could calculate positioning using MagNav.