Integrated Sensing, Computing, and Semantic Communication with Fluid Antenna for Metaverse

TL;DR

This work introduces a fluid-antenna enabled integrated sensing, computing, and semantic communication framework (ISCSC) tailored for the Metaverse, leveraging semantic transmission to reduce data volume and privacy risk while dynamically adapting channels with fluid antennas. An alternating-optimization strategy decomposes the nonconvex joint design into subproblems for ISAC beamforming, FA positioning, and semantic extraction ratio, employing convex surrogates to achieve tractable solutions. The framework accounts for multiple users and extended targets, using an extended-target model and CRB-based sensing metrics alongside semantic secrecy-rate objectives under power and computation constraints. Simulations demonstrate that FA mobility and semantic extraction optimization jointly boost data rates and sensing performance, highlighting the practical potential of FA-enabled ISCSC in immersive, privacy-conscious Metaverse deployments.

Abstract

The integration of sensing and communication (ISAC) is pivotal for the Metaverse but faces challenges like high data volume and privacy concerns. This paper proposes a novel integrated sensing, computing, and semantic communication (ISCSC) framework, which uses semantic communication to transmit only contextual information, reducing data overhead and enhancing efficiency. To address the sensitivity of semantic communication to channel conditions, fluid antennas (FAs) are introduced, enabling dynamic adaptability. The FA-enabled ISCSC framework considers multiple users and extended targets composed of a series of scatterers, formulating a joint optimization problem to maximize the data rate while ensuring sensing accuracy and meeting computational and power constraints. An alternating optimization (AO) method decomposes the problem into subproblems for ISAC beamforming, FA positioning, and semantic extraction. Simulations confirm the framework's effectiveness in improving data rates and sensing performance.

Figures (3)

• Figure 1: A FA-enabled ISCSC system with multiple users and multiple targets.
• Figure 2: Achieved semantic secrecy rate against FAs movable region.
• Figure 3: Worst-case semantic secrecy rate against CRB upper bound.