Neural network channel estimator for 5G and 6G receivers
This technology uses machine learning to teach a wireless receiver how to automatically correct for signal distortions introduced by the environment — things like interference, noise, and multipath fading that degrade communication quality. The system is trained by deliberately sending known signals through a simulated or real channel, then comparing what the receiver actually got against what was originally sent. A neural network learns from that comparison and gets better at estimating and correcting those distortions in real time. The result is a receiver that can adapt to challenging channel conditions without needing hand-crafted signal processing algorithms for every scenario.
What you could build
A software module embedded in 5G/6G base stations, software-defined radios, or satellite communication terminals that uses learned neural networks to replace or augment traditional channel estimation blocks, improving link reliability in dynamic or contested environments. Buyers would be wireless infrastructure OEMs, defense communications integrators, and chipset vendors building next-generation modems.
Who in Virginia should care
Northern Virginia and the Shenandoah corridor host major defense communications integrators (Leidos, SAIC, Booz Allen) and satellite operators who routinely license signal processing IP for fielded systems.
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, Kiran Karra, T. Charles Clancy
- Granted
- May 17, 2022
- Status
- Granted patent
- Patent number
- 11334807
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.