This paper exploits the integrated sensing and communication (ISAC) technology in unmanned aerial vehicle (UAV) networks, where multiple UAVs collaboratively form a virtual antenna array (VAA) within a pre-determined area, to effectively operate as a multi-antenna system for communication and sensing (C&S) services. Since the VAA is an extremely-large antenna array, the near-field characteristics must be considered in C&S channels. By optimizing UAV positions, we construct an enhanced VAA configuration and subsequently design the corresponding beamforming, thereby improving sensing performance while guaranteeing communication requirements. A penalty-based iterative algorithm is exploited to address the resulting optimization problem. Simulation results demonstrate that the optimized VAA with beamforming significantly enhances target localization accuracy compared to conventional schemes, validating the effectiveness of the ISAC implementation in UAV networks.

The phase shift information (PSI) overhead poses a critical challenge to enabling real-time intelligent reflecting surface (IRS)-assisted wireless systems, particularly under dynamic and resource-constrained conditions. In this paper, we propose a lightweight PSI compression framework, termed meta-learning-driven compression and reconstruction network (MCRNet). By leveraging a few-shot adaptation strategy via model-agnostic meta-learning (MAML), MCRNet enables rapid generalization across diverse IRS configurations with minimal retraining overhead. Furthermore, a novel depthwise convolutional gating (DWCG) module is incorporated into the decoder to achieve adaptive local feature modulation with low computational cost, significantly improving decoding efficiency. Extensive simulations demonstrate that MCRNet achieves competitive normalized mean square error performance compared to state-of-the-art baselines across various compression ratios, while substantially reducing model size and inference latency. These results validate the effectiveness of the proposed asymmetric architecture and highlight the practical scalability and real-time applicability of MCRNet for dynamic IRS-assisted wireless deployments.

Integrated sensing and communication (ISAC) is studied in the airborne domain, where Unmanned Aerial Vehicles (UAVs) act as communication base stations and radars simultaneously. The UAV transmits signals to users while leveraging these signals to localize targets. This research focuses on jointly improving communication and sensing (C&S) performances by designing the UAV trajectory and allocating user’s bandwidth. Since UAV’s sustainability is determined by its onboard battery, energy supply is considered as a constraint in the trajectory design. Communication performance is evaluated by total transmitted data, while sensing performance is assessed through Cramér-Rao bound (CRB). A tradeoff objective is formulated with normalization. To achieve a flexible tradeoff between C&S, the trajectory design is formulated as a weighted sum optimization problem. To improve the formulation accuracy of trajectory design, a multi-stage trajectory design (MSTD) is proposed. While the resultant design problem is difficult to solve directly, an iterative algorithm is developed to obtain a local optimal solution of UAV trajectory. Finally, numerical results are presented to show UAV trajectories determined by the tradeoff between C&S and the energy supply. Benefits of ISAC-based UAV scenario are highlighted by comparing the single-functional UAV scenarios.

We consider an unmanned aerial vehicle (UAV) based joint radar localization and communication system, where a UAV transmits the downlink signal to a ground communication user and the transmitted signal is also exploited to localize a target coordinates. We aim to optimize the UAV path with energy constraints. We formulate the trajectory design into a weighted optimization problem, where a scalable performance trade-off between localization and communication can be achieved. An iterative algorithm is exploited then to address the trajectory design formulation. Numerical results are provided to validate the effectiveness of the proposed UAV trajectory design approaches.

By fully exploiting the mobility of unmanned aerial vehicles (UAVs), UAV-based aerial base stations (BSs) can move closer to ground users to achieve better communication conditions. In this paper, we consider a scenario where an aerial BS is dispatched for satisfying the data request of a maximum number of ground users, weighted according to their data demand, before exhausting its on-board energy resources. The resulting trajectory optimization problem is a mixed integer non-linear problem (MINLP) which is challenging solve. Specifically, there are coupling constraints which cannot be solved directly. We exploit a penalty decomposition method to reformulate the optimization formulation into a new form and use block coordinate descent technique to decompose the problem into sub-problems. Then, successive convex approximation technique is applied to tackle non-convex constraints. Finally, we propose a double-loop iterative algorithm for the UAV trajectory design. In addition, to achieve a better coverage performance, the problem of designing the initial trajectory for the UAV trajectory is considered. In the results section, UAV trajectories with the proposed algorithm are shown. Numerical results show the coverage performance with the proposed schemes compared to the benchmarks.

Unmanned Aerial Vehicle (UAV) networks have recently gained interest, owing to the mobility of UAVs that can be exploited to improve channel conditions and user coverage. In this paper, we consider a scenario where a rotary-wing UAV is dispatched for covering a maximum number of ground users by jointly optimizing the UAV trajectory and bandwidth allocation, under constraints of pre-determined maximal total flight time and on-board energy. The problem is difficult to solve since has nonconvex constraints and includes infinite variables over time. As such, we propose an iterative algorithm with guaranteed convergence by applying block coordinate descent and successive convex approximation techniques. We further exploit the path discretization to formulate the original problem into an optimization formulation with finite variables. We deploy a UAV circular trajectory as the benchmark. The numerical results show that the proposed algorithm significantly outperforms the benchmark scheme and the bandwidth allocation can improve UAV coverage compared with the UAV trajectory only with time partitioning.