TTP explores the potential of a pocket-sized passive Radio Frequency (RF) drone detector that combines low-cost RF hardware with low-power Edge AI to address the challenges of non-cooperative Uncrewed Aerial Systems (UAS) detection.
In its whitepaper, Low-cost handheld detection of non-cooperative UAS with edge machine learning, TTP highlights how existing UAS threat mitigation approaches can require expensive radar or camera systems, detailed knowledge of UAS Command and Control (C2) protocols, or cooperative telemetry. Although bulky fixed installations can be highly effective, they can struggle to deliver results for mobile personnel, particularly when discreet operation is required.
TTP’s proof-of-concept system uses machine learning models trained to recognize characteristics of UAS RF emissions, with the potential to detect non-cooperative and previously unseen drones. These lightweight models can run on the processing power available in a mobile phone, with the concept presented as a potential mass-produced solution for routine security or defense applications.
The approach also combines extensive pre-training with a synthetic data generation pipeline to significantly reduce the need for large-scale data collection and labeling. TTP states that, when issued to personnel or used to protect critical infrastructure, the device provides increased situational awareness and robust detection performance in complex, noisy environments.
Download the full whitepaper to learn more about the handheld UAS detection concept, or contact TTP to discuss its further development.




