Transformer based Collaborative Reinforcement Learning for Fluid Antenna System (FAS)-enabled 3D UAV Positioning

2025-07-11

AI Summary

This paper addresses the challenge of real-time, high-precision 3D localization for mobile target unmanned aerial vehicles (UAVs). We propose a novel framework integrating Fluid Antenna Systems (FAS) with multi-agent collaborative optimization. Specifically, we jointly optimize the trajectory of controlled UAVs and the FAS port selection of passive UAVs, enabling decentralized decision-making via an attention-enhanced recurrent multi-agent reinforcement learning (MARL) architecture. Our approach leverages Transformer-based attention to improve global Q-function approximation, employs RNNs to model temporal dependencies, and fuses FAS-reflected signals with distance estimates to achieve accurate 3D localization. Experimental results demonstrate that our method reduces average localization error by 17.5% compared to VD-MARL and by 58.5% relative to a non-FAS baseline, significantly enhancing real-time localization performance in dynamic environments.

Technology Category

• Multiagent Systems: Adversarial Agents
• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

In this paper, a novel Three dimensional (3D) positioning framework of fluid antenna system (FAS)-enabled unmanned aerial vehicles (UAVs) is developed. In the proposed framework, a set of controlled UAVs cooperatively estimate the real-time 3D position of a target UAV. Here, the active UAV transmits a measurement signal to the passive UAVs via the reflection from the target UAV. Each passive UAV estimates the distance of the active-target-passive UAV link and selects an antenna port to share the distance information with the base station (BS) that calculates the real-time position of the target UAV. As the target UAV is moving due to its task operation, the controlled UAVs must optimize their trajectories and select optimal antenna port, aiming to estimate the real-time position of the target UAV. We formulate this problem as an optimization problem to minimize the target UAV positioning error via optimizing the trajectories of all controlled UAVs and antenna port selection of passive UAVs. Here, an attention-based recurrent multi-agent reinforcement learning (AR-MARL) scheme is proposed, which enables each controlled UAV to use the local Q function to determine its trajectory and antenna port while optimizing the target UAV positioning performance without knowing the trajectories and antenna port selections of other controlled UAVs. Different from current MARL methods, the proposed method uses a recurrent neural network (RNN) that incorporates historical state-action pairs of each controlled UAV, and an attention mechanism to analyze the importance of these historical state-action pairs, thus improving the global Q function approximation accuracy and the target UAV positioning accuracy. Simulation results show that the proposed AR-MARL scheme can reduce the average positioning error by up to 17.5% and 58.5% compared to the VD-MARL scheme and the proposed method without FAS.

Problem

• Estimating real-time 3D position of moving target UAV
• Optimizing trajectories and antenna port selection for UAVs
• Improving positioning accuracy via attention-based reinforcement learning

Innovation

• Transformer-based reinforcement learning for UAV positioning
• Attention mechanism enhances historical state-action analysis
• Recurrent neural network improves Q function accuracy