PIPages
Labs

Vuk Marojevic

Mississippi State University, MS·Engineering

Wireless signals are filling more and more of the radio spectrum, and these networks are getting more complex. This creates two related problems.

Write an email
Fields

Engineering

Computer Science

Earth & Environmental Science

Topics

radio frequency interference

passive radiometers

microwave radiometry

Grants
2 known grants, through Sep 2027

What they work on

  1. Build a passive microwave radiometer flown on a drone on the AERPAW testbed to collect the first large active/passive radio coexistence dataset with ground-truth information.
  2. Develop a digital twin, a simulated copy of the drone radiometer within the AERPAW emulation environment, so researchers can run realistic interference-mitigation experiments in the cloud.
  3. Create data-driven, end-to-end learning methods that run on the radiometer itself to detect interference across time and frequency, calibrate the radiometer and recover the true scientific signal.
  4. Develop deep reinforcement learning and subspace-based methods for reducing interference, using feedback from both active transmitters and passive sensors.
  5. Build OAIC-C, an open-source library of AI controllers for 6G Open Radio Access Networks that runs on common software-defined radio platforms.
  6. Build OAIC-T, an AI testing framework and set of verification tools, for systematic, exhaustive testing on community wireless research testbeds.

More about the research

Cell phone and satellite transmissions can drown out the faint natural radio signals that passive radiometers collect. Radiometers are instruments that measure natural radio emission for weather and environmental monitoring. At the same time, future cellular networks will rely on artificial intelligence (AI) to manage the radio spectrum, but researchers lack shared, open tools for building and testing such systems. This work tackles both problems with real-world radio datasets, machine learning and open software for radio experiments.

Why it matters

Satellites and sensors that monitor weather and the atmosphere depend on passive radiometers. Methods for detecting and removing interference could protect these measurements as wireless networks expand and could help the two kinds of systems share the spectrum. Open AI cellular software could speed up research on 6G networks and inform standards and regulatory decisions. Other agencies could also use it to build cellular systems for transportation and smart grid applications.

Known grants

From NIH and NSF research grants. Labs often have other funding we can't see.

Collaborative Research: CCRI: New: Open AI Cellular (OAIC): Prototyping Artificial Intelligence-Enabled Control and Testing Systems for Cellular Communications Research

NSF · Oct 2021 – Sep 2027

Collaborative Research: SWIFT-SAT: INtegrated Testbed Ensuring Resilient Active/Passive CoexisTence (INTERACT): End-to-End Learning-Based Interference Mitigation for Radiometers

NSF · Jan 2024 – Dec 2026

Closest labs

Neal Patwari

Washington University in St Louis, MO·Engineering

Develop RF watermarks that embed random pseudonyms in wireless signals so that passive radio receivers, such as radio telescopes, can identify any interfering transmitter.

Aly Sabri Abdalla

Mississippi State University, MS·Engineering

Characterize O-RAN attacks caused by out-of-sync state changes, timing-induced protocol deviations, malicious user devices and unstable control-app decisions.

Guevara Noubir

Northeastern University, MA·Engineering

Analyze threats to spectrum sharing from adversaries who use software-defined radios and machine learning to evade detection, including colluding transmitters.

The school

Mississippi State University: 9 labs on PI Pages, $342M a year on research, 168 research doctorates a year.

More about Mississippi State University

Reach out

A start for your email. Fill in the brackets.