Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Agentic Physical-AI for Self-Aware RF Systems

Linuka Ratnayake, Danidu Dabare, Sanuja Rupasinghe, Warren Jayakumar, Dileepa Marasinghe, Chamira U. S. Edussooriya, Arjuna Madanayake

Abstract

Intelligent control of RF transceivers adapting to dynamic operational conditions is essential in the modern and future communication systems. We propose a multi-agent neurosymbolic AI system, where AI agents are assigned for circuit components. Agents have an internal model and a corresponding control algorithm as its constituents. Modeling of the IF amplifier shows promising results, where the same approach can be extended to all the components, thus creating a fully intelligent RF system.

Agentic Physical-AI for Self-Aware RF Systems

Abstract

Intelligent control of RF transceivers adapting to dynamic operational conditions is essential in the modern and future communication systems. We propose a multi-agent neurosymbolic AI system, where AI agents are assigned for circuit components. Agents have an internal model and a corresponding control algorithm as its constituents. Modeling of the IF amplifier shows promising results, where the same approach can be extended to all the components, thus creating a fully intelligent RF system.
Paper Structure (4 sections, 3 figures)

This paper contains 4 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Multi-agent RF Transceiver Architecture
  3. Preliminary Results
  4. Discussion and Conclusion

Figures (3)

  • Figure 1: System architecture shows that the multi-agent AI framework optimizes the physical RF receiver using a neurosymbolic architecture driven by real-time signal features (STFT, EVM) and sensor feedback.
  • Figure 2: Input and output power spectral densities shows that the ARVTDNN model accurately replicates the frequency response of the IF amplifier, validating the digital twin.
  • Figure 3: Scatter plot of AM/AM compression of the input vs. output envelope amplitude shows that the model successfully captures the IF amplifier's nonlinear gain characteristics and memory effects.