Toward Intelligent Antenna Positioning: Leveraging DRL for FAS-Aided ISAC Systems
Shunxing Yang, Junteng Yao, Jie Tang, Te‐Kao Wu, Maged Elkashlan, Chau Yuen, Mérouane Debbah, Hyundong Shin, Matthew C. Valenti
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. Unlike traditional optimization approaches that suffer from exponential complexity growth, our DRL-based method achieves real-time decision-making with superior scalability for complex multi-target scenarios while maintaining computational efficiency.