Quantum Magnetic Fingerprinting for GNSS-Denied Navigation in Urban Air Mobility: A Machine Learning Approach from Ground to Altitude

GPS works poorly in dense city environments because tall buildings block satellite signals. This project will test whether a new type of ultra-sensitive sensor—a quantum magnetometer that measures tiny changes in the Earth’s magnetic field—can help drones and future flying taxis (Urban Air Mobility) figure out where they are when GPS fails. The research team will first build detailed magnetic “fingerprint” maps at ground level in outdoor urban spaces, then fly a drone at different heights (up to 100 meters) to see if those same magnetic patterns can still be recognized from the air. Using machine learning, they will develop software that predicts a drone’s location based on the magnetic field it measures. The expected benefit for the participating institutions is twofold: the host university (in Canada) will gain unique datasets and advance its leadership in quantum sensing and drone navigation, while the partner university (in South Korea) will bring back specialized expertise in field-testing quantum sensors and integrating them with artificial intelligence—creating a lasting research collaboration between the two countries.

Faculty Supervisor:

Ajmery Sultana

Student:

Partner:

Hanseo University

Discipline:

Computer science

Sector:

Aerospace; Quantum Science; Technology

University:

Algoma University

Program: