Far above yours The head, constellations of satellites are constantly working to provide the positioning, navigation and timing systems that peacefully power newfangled life. The signals from these satellites, known as the Global Navigation Satellite System (GNSS), underpin mobile networks, power grids, the Internet and GPS. Their reliability is increasingly at risk.
GPS signals can be jammed – intentionally jammed with other robust radio signals – and spoofed, releasing erroneous signals to fool positioning systems. GPS interference has been documented in Ukraine, Middle Eastand South China Sea.
However, startup SandboxAQ believes that artificial intelligence combined with navigation systems that read the Earth’s magnetic field, known as MagNav, can mitigate these threats to GNSS. “Our technology is not a replacement [GNSS]but can enhance existing navigation systems to improve safety and serve as an alternative primary navigation source in the event of GPS failure,” says Luca Ferrara, general manager of SandboxAQ navigation department.
SandboxAQ’s navigation technology, called AQNav, uses quantum magnetometers – devices that can very precisely detect changes in the magnetic field by measuring subatomic particles – to obtain a reading of the Earth’s magnetic field. “We’re looking for the unique fingerprint of magnetized rock formations in the Earth’s crust,” Ferrara says.
Artificial intelligence is then used to pinpoint the aircraft’s position by comparing it with known magnetic field maps. Artificial intelligence also eliminates any external disturbances generated by the aircraft, such as sudden movements or signals from its electrical systems; individual aircraft have unique characteristics when it comes to introducing magnetic disturbances.
So far, the US Air Force, Boeing and Airbus have done this all test flights performed using the system. “Since May 2023, we have deployed and tested multiple versions of our hardware and software,” explains Ferrara. “AQNav has flown hundreds of kilometers in a variety of aircraft types, from single-engine aircraft to large military transports. It was tested in real flight scenarios, including two large military exercises conducted by the U.S. Air Force.”
The SandboxAQ team – and the inspiration for the idea – was formed at Google’s parent company, Alphabet, between 2016 and 2022. The initial idea was to find applications for artificial intelligence and quantum technologies developed at Google’s Moonshot factory.