AI-Limited Fluid Antenna-Aided Integrated Sensing and Communication Systems

2026-02-05

AI Summary

This work investigates the fundamental performance limits of integrated sensing and communication (ISAC) under the joint constraints of an artificial intelligence (AI) representation bottleneck and a fluid antenna system. Information is encoded into Gaussian waveforms and mapped by a capacity-constrained AI encoder into latent representations that serve as channel inputs. At the receiver, optimal port selection in the fluid antenna enhances system performance. Theoretical analysis reveals that the AI bottleneck is equivalent to additive representation noise, enabling the first characterization of the ISAC rate–distortion region under both AI-induced constraints and antenna port selection. It is further shown that the achievable gain from port selection is fundamentally limited by the physical antenna length. Leveraging information-theoretic tools, Jakes channel modeling, and duality-based bounding techniques, tight achievability and converse bounds are derived, demonstrating that increasing antenna length allows communication rates and sensing mean-square error to approach the theoretical limits imposed by the AI bottleneck, as confirmed by numerical experiments.

Technology Category

• Humans and AI: Brain-Sensing and Analysis
• Machine Learning: Information Theory
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Security and privacy of machine learning and AI applications
• Search and Retrieval-Augmented AI: Agentic search

Abstract

This paper characterizes the fundamental limits of integrated sensing and communication (ISAC) when the transmitter is subject to an artificial intelligence (AI) representation bottleneck and the receiver employs a fluid antenna system (FAS). Specifically, the message is first encoded into an ideal Gaussian waveform and mapped by an AI encoder into a finite-capacity latent representation that constitutes the physical channel input, while the FAS receiver selects the port experiencing the most favorable channel conditions. We reveal that the AI bottleneck is equivalent to an additive representation noise, which reduces both the communication and sensing signal-to-noise ratios (SNRs) at the selected port. We then derive the resulting ISAC capacitydistortion region and establish tight converse and achievability bounds under general fading models, including Jakes-correlated channels. Leveraging the spatial degrees of freedom (DoF) characterization of the Jakes'model, we furthermore prove that the port-selection gain is fundamentally constrained by the physical length of the FAS region: the effective diversity order equals the numerical rank of the Jakes'correlation matrix and increases only with the FAS length. Consequently, enlarging the FAS length allows the selected-port SNR to approach the AI-imposed ceiling, driving the achievable communication rate and sensing mean square error (MSE) toward their AI-limited fundamental bounds. Numerical results corroborate the analysis and scaling laws.

Problem

• Integrated Sensing and Communication
• AI bottleneck
• Fluid Antenna System
• Capacity-Distortion Region
• Spatial Degrees of Freedom

Innovation

• AI representation bottleneck
• fluid antenna system (FAS)
• integrated sensing and communication (ISAC)
• capacity-distortion region
• spatial degrees of freedom