ML-driven adaptive radio front-end for dynamic RF environments
This technology uses machine learning to automatically tune a radio receiver's antenna and amplifier settings in real time, optimizing how it captures and processes incoming wireless signals. Rather than relying on fixed hardware configurations, the system observes signal quality metrics after each adjustment, stores those observations, and updates its policies to make better decisions on the next signal. Think of it as a self-improving radio that learns from experience to consistently pull in the clearest possible signal under changing conditions. The reinforcement learning approach means the system gets smarter over time without requiring manual reconfiguration by engineers.
What you could build
An adaptive radio front-end module or software layer that auto-optimizes antenna orientation and gain settings for wireless base stations, software-defined radios, or IoT gateways — sold to telecom equipment vendors, defense radio manufacturers, or industrial wireless OEMs seeking resilient connectivity in contested or variable RF environments.
Who in Virginia should care
Defense contractors and system integrators in Northern Virginia and the Hampton Roads corridor — such as those supporting Navy and DoD communications programs — would have direct interest in adaptive RF signal processing for contested spectrum environments.
Readiness: Lab validated
Concept — described but not yet demonstrated. Lab validated — supported by experimental results in the patent. Prototype likely — the text describes a built, working embodiment.
Readiness is inferred from the patent text, not from a lab visit.
The record
- Inventors
- Timothy James O`Shea, Thomas Charles Clancy III
- Granted
- May 30, 2023
- Status
- Granted patent
- Patent number
- 11664910
Ready to talk?
Virginia Tech Intellectual Properties handles licensing for this technology.
Prosim summaries are generated from public patent text and are not legal advice.