Towards Intelligent Antenna Positioning: Leveraging DRL for FAS-Aided ISAC Systems

TL;DR

This paper introduces a DRL-based framework for intelligent fluid antenna positioning in ISAC systems, addressing multi-target sensing and joint beamforming optimization challenges with scalable solutions.

Contribution

It proposes a novel BCD framework combined with DDPG to optimize antenna positions and beamforming in complex multi-target scenarios.

Findings

Effective balancing of sensing and communication performance.

Scalable approach demonstrated through simulations.

Improved antenna positioning in multi-target environments.

Abstract

Fluid antenna systems (FAS) enable dynamic antenna positioning, offering new opportunities to enhance integrated sensing and communication (ISAC) performance. However, existing studies primarily focus on communication enhancement or single-target sensing, leaving multi-target scenarios underexplored. Additionally, the joint optimization of beamforming and antenna positions poses a highly non-convex problem, with traditional methods becoming impractical as the number of fluid antennas increases. To address these challenges, this letter proposes a block coordinate descent (BCD) framework integrated with a deep reinforcement learning (DRL)-based approach for intelligent antenna positioning. By leveraging the deep deterministic policy gradient (DDPG) algorithm, the proposed framework efficiently balances sensing and communication performance. Simulation results demonstrate the scalability and effectiveness of the proposed approach.