In this paper, channel estimation (CE) for up-link hybrid-field communications involving multiple Internet of Things (IoT) devices assisted by an active intelligent reflecting surface (IRS) is investigated. Firstly, to reduce the complexity of near-field (NF) channel modeling and estimation between IoT devices and active IRS, a sub-blocking strategy for active IRS is proposed. Specifically, the entire active IRS is divided into multiple smaller sub-blocks, so that IoT devices are located in the far-field (FF) region of each sub-block, while also being located in the NF region of the entire active IRS. This strategy significantly simplifies the channel model and reduces the parameter estimation dimension by decoupling the high-dimensional NF channel parameter space into low dimensional FF sub channels. Subsequently, the relationship between channel approximation error and CE error with respect to the number of sub-blocks is derived, and the optimal number of sub-blocks is solved based on the criterion of minimizing the total error. In addition, considering that the amplification capability of active IRS requires power consumption, a closed-form expression for the optimal power allocation factor is derived. To further reduce the pilot overhead, a lightweight CE algorithm based on convolutional autoencoder (CAE) and multi-head attention mechanism, called CAEformer, is designed. The Cramér-Rao lower bound is derived to evaluate the proposed algorithm’s performance. Finally, simulation results demonstrate the proposed CAEformer network significantly outperforms the conventional least square and minimum mean square error scheme in terms of estimation accuracy.

Cooperated with simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) and unmanned aerial vehicle (UAV), a non-orthogonal multiple access (NOMA) covert communication network is conceived. However, open channels are more vulnerable to eavesdropping byWardens, overlying that the channel state information (CSI) may be unstable with UAV’s time-varying deployments. In this paper, a deep reinforcement learning (DRL)-based and instantaneous channel-deducted framework is investigated for resolving the cutting-edge maximization problem of covert communication rate, subjected to the UAV flight, QoS requirement, and communication covertness. Given the channels instability caused by time-varying UAV flight, we design a channel deduction network by integrating complex-domain multi-layer perceptron (CMixer) and recurrence-based bidirectional long-short term memory (BiLSTM) to exploit the nonlinear correlations of channels in time, spatial location, and antenna domains. Relying on the states with deducted channels, the Twin Delayed Deep Deterministic policy gradient (TD3) as a proactive and policy-based DRL algorithm is used to iteratively train an agent responsible for adaptive adjusting UAV deployment and STAR-RIS beamforming. Simulation results demonstrate the effectiveness of the proposed channel deduction scheme, covert communication mechanism, and their synthesis.

The flexibility and maneuverability of unmanned aerial vehicles (UAVs) lend themselves to tracking users and operating as an aerial base station carrying out communication enhancement functionality. A core challenge neglected by most existing works is that the true-but-unknown obstacles can jeopardize UAV flight security and shadow its communication links with users, resulting in poor achievable rate and high collision risks. In this paper, a deep-reinforcement-learning (DRL)-based UAV target tracking and digital-twin (DT)-assisted collision avoidance method is proposed to optimize UAV’s communication performance while tracking moving users. Toward this end, Twin Delayed Deep Deterministic policy gradient (TD3) as a novel and policy-based DRL algorithm is used to construct an agent responsible for adaptive deciding UAV flying control actions. To efficiently detect unknown obstacles in a flight environment, an orthogonal frequency division multiple (OFDM)-based integrated sensing and communication (ISAC) system is investigated, endowing UAV’s agent with real-time obstacle distance. Finally, we present a DT obstacle model construction mechanism and integrate it with TD3 agent training. The extensive simulations demonstrate the reward convergence of the TD3 algorithm and the communication improvement with stable user tracking and reliable collision avoidance, compared with conventional approaches.