Back to the portfolio

Neural network channel estimator for 5G and 6G radios

Communications & RFComputing, Software & AIDefense & Aerospace ApplicationsPrototype likely

This technology uses machine learning to help wireless receivers better understand and compensate for the distortions a radio signal picks up as it travels through the air. Traditional receivers rely on known mathematical models to estimate how a channel scrambles a signal, but real-world conditions are complex and variable. This system trains a neural network on simulated impairments that mimic real channel effects, then deploys that network to continuously estimate and correct signal distortions in live communications. The result is a cleaner, more accurately recovered signal with less reliance on hand-crafted algorithms.

What you could build

A software module or firmware component embedded in 5G/6G base stations, software-defined radios, or satellite receivers that replaces or augments conventional channel estimators with a trained neural network; telecom equipment OEMs and defense radio system integrators would be the primary buyers.

Who in Virginia should care

Northern Virginia and the Hampton Roads corridor host major defense contractors, SIGINT primes, and commercial satellite operators who routinely upgrade radio receiver software and would evaluate this for tactical radios or LEO ground terminals.

Readiness: Prototype likely

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, Kiran Karra, T. Charles Clancy
Granted
February 11, 2025
Status
Granted patent
Patent number
12223443

Ready to talk?

Virginia Tech Intellectual Properties handles licensing for this technology.

VTIP contact coming shortly

Prosim summaries are generated from public patent text and are not legal advice.