Low-Cost Sensor Identifies Incoming Drones by Motor Magnetic Fields
Florida International University engineers achieve 98.5 percent detection accuracy using passive low-frequency radio sensing and artificial intelligence
By Letizia Giugliano
2 min readHuman-Edited, AI-Assisted
Engineers at Florida International University have created a passive detection method that identifies airborne drones solely through the magnetic signatures produced by their electric motors. The hardware costs only a few hundred dollars to assemble and pinpoints drone models with up to 98.52% accuracy at close range, offering an alternative to active radar and noisy acoustic systems.
Reading the Invisible Magnetic Footprint of Drone Motors
Small, mass-producible unmanned aircraft known as micro-UAS pose severe detection challenges on modern battlefields because they often fly under the threshold of conventional radar. To address this vulnerability, an innovation by researchers at Florida International University turned to an unavoidable physical byproduct of multirotor flight: the extremely low frequency (ELF) magnetic fields created by spinning electric motors, as detailed by TechXplore. Because commercial and tactical drones employ distinct motor numbers, geometries, and electrical layouts, every model emits a distinct electromagnetic signature while airborne.
“Every detection method currently in use gives something away. Radar transmits a signal. Acoustic systems get overwhelmed by background noise. We went a different direction entirely.”
— Arjuna Madanayake, Professor at Florida International University
Machine Learning and Passive Antenna Architecture
Rather than projecting active radio beams, the detection apparatus operates entirely silently. A specialized receiver antenna captures incoming ambient emissions, which are subsequently analyzed by an artificial intelligence and machine learning model trained to recognize specific motor patterns, according to TechXplore. In field trials published in the journal IEEE Sensors Journal under the study ELF Passive Radio Sensing and AI-Perception of Micro-UAS, the system achieved 98.52% accuracy in outdoor settings at ranges reaching 15 meters (49 feet), correctly reporting not only that an aircraft was present but identifying its exact make and model.
Low Production Cost and Zero Signal Emission
Conventional tracking systems carry structural trade-offs: radar units transmit signals that expose the operator's position, while optical cameras require line of sight and acoustic microphones struggle in windy or loud combat environments. By contrast, the FIU prototype passively listens without broadcasting a return signature, leaving zero detectable electronic trace, as reported by TechXplore. The development was directed by Professor Arjuna Madanayake from FIU's Department of Electrical & Computer Engineering, working alongside Sri Lanka-based researcher Chatura Seneviratne and Soumyajit Mandal of Brookhaven National Laboratory.
Industry Collaboration and Future Deployment
The economic barrier to counter-drone monitoring could drop significantly if the technology scales, given that the underlying hardware costs only a few hundred dollars and requires no specialized on-site operational crew, notes TechXplore. With the United States Department of War requesting $74 billion for drone and counter-drone systems in its fiscal 2027 budget, the university research group is actively collaborating with American industrial partners to expand detection range and bring the passive tracking invention to commercial defense applications.
Read also on The Patent: Lab-Grown Neurons Decode Braille and Steer Robot Dogs
