The low-altitude intelligent networks (LAINs) emerge as a promising architecture for delivering low-latency and energy-efficient edge intelligence in dynamic and infrastructure-limited environments. By integrating unmanned aerial vehicles (UAVs), aerial base stations, and terrestrial base stations, LAINs can support mission-critical applications such as disaster response, environmental monitoring, and real-time sensing. However, these systems face key challenges, including energy-constrained UAVs, stochastic task arrivals, and heterogeneous computing resources. To address these issues, we propose an integrated air-ground collaborative network and formulate a time-dependent integer nonlinear programming problem that jointly optimizes UAV trajectory planning and task offloading decisions. The problem is challenging to solve due to temporal coupling among decision variables. Therefore, we design a hierarchical learning framework with two timescales. At the large timescale, a Vickrey-Clarke-Groves auction mechanism enables the energy-aware and incentive-compatible trajectory assignment. At the small timescale, we propose the diffusion-heterogeneous-agent proximal policy optimization, a generative multi-agent reinforcement learning algorithm that embeds latent diffusion models into actor networks. Each UAV samples actions from a Gaussian prior and refines them via observation-conditioned denoising, enhancing adaptability and policy diversity. Extensive simulations show that our framework outperforms baselines in energy efficiency, task success rate, and convergence performance.

Intelligent air-ground integration communication is an emerging technology. Uncrewed aerial vehicles (UAVs) serve as mobile edge computing (MEC) servers in large-scale Internet of Things (IoT) applications, alleviating the computational load on ground users. Existing multi-UAV MEC approaches struggle with the complex computation and large data sizes of deep neural network tasks. To address these challenges, we propose a Deep Reinforcement Learning (DRL)-based DNN Partitioning and Dynamic Trajectory Selection (DPDTS) method, which reduces end-to-end latency and system energy consumption through task offloading and collaborative inference. Specifically, we propose an Optimal Partition Point Selection (OPPS) algorithm to minimize transmission overhead by selecting optimal partition points for DNN tasks. Then, we design a fairness-based matching algorithm to optimize user offloading and resource allocation. Finally, OPPS and matching algorithms are integrated to optimize UAV flight trajectories and user transmission power via DRL. The simulation results show that DPDTS outperforms existing benchmark methods in terms of delay and energy efficiency.

The exploitation of unmanned aerial vehicles (UAVs) as mobile relays to establish line-of-sight (LoS) links for free space optical (FSO) communications has shown significant potential. However, adverse weather conditions and pointing errors substantially affect the communication quality of FSO. Therefore, in this paper, an optical reconfigurable intelligent surface (ORIS)-assisted UAV relay FSO communications network is conceived, which is capable of adaptively offering high-quality communication services for mobile targets. To maximize the system’s ergodic capacity, a simulated annealing assisted double deep Q-network (SA-DDQN) method is proposed, which enhances system effectiveness by jointly optimizing the ORIS phase shift and UAV trajectory. Simulation results show that the proposed method is capable of adaptively formulating the trajectory of UAV in light of the user’s location and leads to an enhancement in ergodic capacity compared to the traditional UAV relay scheme under the same conditions.

In some UAV networks (Unmanned Aerial Vehicle networks), data is sent from UAVs to a backend server through gateway UAVs in real time. To avoid a single point of failure, using multiple gateways is preferred so that a UAV can switch to another one if a gateway fails. However, we find that the combination of current routing protocols and the IP protocol stack leads to slow switching, usually over 20 seconds. In this paper, we propose a Quick Gateway Switching approach (QGSwitch) for UAV networks with multiple gateways. QGSwitch uses the Batman-adv routing protocol, a built-in module in the Linux kernel, to establish an ad hoc network. With QGSwitch, UAVs do not need to change their IP settings when a gateway fails because the switching is done at the data link layer. To reduce the delay caused by passive failure detection, QGSwitch improves neighbor discovery and its link with the routing protocol. We implement QGSwitch on Raspberry Pi computers and conduct evaluations in both indoor and outdoor environments. Results show that QGSwitch reduces the average gateway switching delay to 1.24 seconds, which is quicker than Batman-adv with 36.48 seconds and OLSR with 20.43 seconds. It also outperforms both baselines in terms of packet loss and throughput.

Considering their high mobility and relatively low cost, uncrewed aerial vehicles (UAVs) equipped with mobile base stations are regarded as a potential technological approach. However, the dual pressures of limited onboard resources of UAVs and the demand for high-quality services in dynamic low-altitude applications jointly form a bottleneck for system performance. Although multi-UAVs communication networks can provide higher system performance through coordinated deployment, the challenges of cooperation and competition among UAVs, as well as more complex optimization problems, significantly increase costs and pose formidable challenges. To overcome the challenges of low coordination efficiency and intense resource competition among multiple UAVs, and to ensure the timely and efficient satisfaction of ground users (GUs) communication service demands, this paper conceives a centralized-controlled two-tier-cooperated UAVs communication network. The network comprises a central UAV (C-UAV) tier as control center and a marginal UAV (M-UAV) tier to serve GUs. In response to the increasingly dynamic and complex scenarios, along with the challenge of insufficient generalization ability in Deep Reinforcement Learning (DRL) algorithms, we propose a clustering-assisted dual-agent soft actor critic (CDA-SAC) algorithm for trajectory design and resource allocation, aiming to maximize the fair energy efficiency of the system. Specifically, by integrating a clustering-matching method with a dual-agent strategy, the proposed CDA-SAC algorithm achieves significant improvements in generalization ability and exploration capability. Simulation results demonstrate that the proposed CDA-SAC algorithm can be deployed without retraining in scenarios with different numbers of GUs. Furthermore, the CDA-SAC algorithm outperforms both the multi-UAV scenarios based on the MADDPG algorithm and the FDMA scheme in terms of fairness and total energy efficiency.

The emergence of high-frequency base stations (BSs) and heterogeneous network architectures has enhanced UAV-augmented cell-free (CF) networks for providing ubiquitous access and high-speed transmission. However, these networks still face challenges such as multi-user interference and multi-BS selection, particularly during data bursts or load imbalance. This paper proposes a cognitive pilot-driven resource optimization (CPDRO) framework for UAV-augmented CF networks, including a greedy pilot sequence assignment (GPSA) algorithm, a BS access mechanism based on estimated channel gain, and an alternating direction method of multipliers with water-filling based power allocation (ADMM-WFPA) algorithm. First, users allocate limited-bandwidth pilot signals to all BSs using a two-stage GPSA algorithm, which combines random initialization followed by greedy optimization to minimize pilot contamination. Second, based on the estimated channel gains obtained from the pilots, users select the appropriate BSs for access to maximize resource utilization efficiency. Finally, after connecting to the assigned BS, users employ the ADMM-WFPA algorithm, which integrates exploration and exploitation, to batch-optimize power resource allocation among users. These three modules operate iteratively to achieve cognitive awareness of the network environment, enabling adaptive decision-making that aligns with real-time network conditions. We then simulate the proposed framework's performance, comparing it with random and ADMM framework. Results show that the proposed framework outperforms the direct ADMM by more than 24.98% in ergodic sum rate improvement.

Accurate three-dimensional (3D) mapping of underwater environments is critical for marine resource assessment and underwater archaeological investigations, where measurement accuracy and completeness are often challenged by optical distortion and platform motion. Stereo vision provides a promising solution for underwater 3D measurement; however, refraction effects and localization instability significantly degrade mapping performance. This study proposes a stereo vision–based framework for accurate 3D coverage mapping using autonomous underwater vehicles (AUVs). The framework integrates three measurement-oriented modules: a refraction-compensated stereo camera calibration method to improve underwater geometric consistency; a hybrid visual simultaneous localization and mapping (SLAM) scheme that fuses monocular and stereo visual cues to enhance tracking stability and localization accuracy; and a coverage mapping strategy based on image feature alignment, offset vector correction, and dense 3D reconstruction to achieve complete scene coverage with controlled redundancy. Controlled tank experiments are conducted to evaluate the proposed framework. Experimental results show that the refraction-compensated calibration reduces reprojection error by 32.5%. Compared with monocular SLAM, the proposed hybrid SLAM reduces the Root Mean Square (RMS) absolute translation error from 0.6642 m to 0.1489 m, corresponding to a 77.6% improvement, while achieving improved tracking continuity compared with stereo SLAM under identical conditions. Robustness evaluation under representative underwater image degradation conditions indicates that the proposed method maintains stable localization performance with limited degradation under spectral attenuation, scattering, and low-illumination noise. The proposed coverage mapping strategy enables complete 3D reconstruction through offset-vector-based motion compensation. These results demonstrate the effectiveness and reliability of the proposed framework for underwater 3D measurement and mapping applications.

A pinching antenna system (PASS) assisted cognitive radio (CR) system is proposed. A secondary system sum rate maximization problem is formulated by jointly considering the base station (BS) power budget, the pinching antenna (PA) deployment constraints, and the interference tolerance requirements of primary users. To address the resulting non-convex problem, a tractable reformulation based on the weighted minimum mean-square error (WMMSE) approach is adopted, followed by the development of an alternating optimization (AO) algorithm. Within this framework, the auxiliary variables are updated in closed form, enabling an efficient transformation of the digital beamforming subproblem to a convex form, while the PA deployment is refined through a tailored element-wise optimization strategy. Numerical results validate the effectiveness of the proposed design and show consistent performance gains compared with conventional benchmark schemes.

Free-space optical (FSO) communications technology has been widely applied in uncrewed aerial vehicle (UAV) networks to offer the ambitious large-capacity, high-security, and interference-immuned links. However, due to atmospheric disturbances at low-altitude airspace as well as flexible-mobility and jitter of the UAV platform, the FSO link between UAVs often suffers from frequent beam misalignment, leading to undesired interruption of communications. Therefore, in this letter, we conceive a UAV-to-UAV (U2U) FSO beam alignment system, where an adaptive exploration driven deep deterministic policy gradient (AED-DDPG) algorithm is proposed to enhance the FSO link quality. By jointly optimizing transmit power and divergence angle at the transmitter site, associated to the field-of-view (FoV) angle at the receiver site, the minimized outage probability can be consequently attained. Our simulation results demonstrate that the proposed method effectively improves the FSO beam alignment of the U2U link under dynamic conditions, which further enhances the robustness of the UAV-FSO system.

Unmanned Aerial Vehicles (UAV) networks face numerous challenges in dynamic jamming environments, particularly when frequent short-term fluctuations in link quality occur. Traditional routing protocols operate at the network layer, and there is a latency in feedback on link quality. Frequent fluctuations may even lead to route oscillations and packet loss. To address this challenge, this paper proposes a cooperative cross-layer routing (CoRt), breaking away from traditional models by allowing the network layer routing protocol to plan multiple route paths and provide several candidate next hops to the link layer. The link layer dynamically selects the optimal next hop based on related jamming information, thus avoiding issues such as delayed link quality updates and route oscillations. Additionally, this approach offers greater flexibility for optimization at both the network and link layers. We implement the protocol on a commercial network simulator EXata. The results demonstrate the effectiveness of our routing protocol in complex dynamic environments, significantly improving the communication stability and efficiency of UAV networks.

To enhance the sustained mission capability of large-scale UAV(unmanned aerial vehicle)swarms facing both soft and hard-kill threats,this research focused on swarm topology reconstruction methods.Addressing the issue of node failures,a dynamic control authority migration mechanism under a centralized-distributed hybrid control architecture was proposed to improve reconstruction efficiency;concurrently,an SDN(software-defined network)-based elastic networking architecture was designed,integrating intent-driven principles to enable intelligent and dynamic configuration of network resources.Simulation comparisons were conducted between dual-mode reconstruction strategies:neighbor autonomous compensation and resource-pool dynamic scheduling.When facing small-scale node loss,neighbor compensation leverages its advantage in local decision-making,reducing the average reconstruction latency by 38.5％compared to resource-pool scheduling.However,as the number of failed nodes increases,the combined centralized-distributed controller strategy achieves the shortest reconstruction time;notably,under persistent electromagnetic interference environments,this combined strategy demonstrates significant advantages,reducing latency by 18.3％compared to a purely distributed approach.This research provides theoretical support and practical reference for topology reconstruction in large-scale UAV swarms.

The expansion of the low-altitude economy has underscored the significance of Low-Altitude Network Coverage (LANC) prediction for designing aerial corridors. While accurate LANC forecasting hinges on the antenna beam patterns of Base Stations (BSs), these patterns are typically proprietary and not readily accessible. Operational parameters of BSs, which inherently contain beam information, offer an opportunity for data-driven low-altitude coverage prediction. However, collecting extensive low-altitude road test data is cost-prohibitive, often yielding only sparse samples per BS. This scarcity results in two primary challenges: imbalanced feature sampling due to limited variability in high-dimensional operational parameters against the backdrop of substantial changes in low-dimensional sampling locations, and diminished generalizability stemming from insufficient data samples. To overcome these obstacles, we introduce a dual strategy comprising expert knowledge-based feature compression and disentangled representation learning. The former reduces feature space complexity by leveraging communications expertise, while the latter enhances model generalizability through the integration of propagation models and distinct subnetworks that capture and aggregate the semantic representations of latent features. Experimental evaluation con firms the efficacy of our framework, yielding a 7% reduction in error compared to the best baseline algorithm. Real-network validations further attest to its reliability, achieving practical prediction accuracy with MAE errors at the 5 dB level.

To meet the demands for comprehensive three-dimensional coverage and massive connectivity in sixth generation of communication system （6G）， establishing a space-air-ground integrated networks （SAGIN） has become a crucial development direction. However， both standalone radio frequency （RF） and free-space optical （FSO） communication technologies have inherent limitations， making it challenging for either to independently fulfill the future network’s comprehensive requirements for ultra-high speed， ultra-high reliability， and wide-area dynamic access. Against this backdrop， integrating the complementary advantages of RF and FSO communications to build an intelligent and cooperative hybrid RF/FSO transmission network for SAGIN has become a key pathway to overcoming current technological bottlenecks. This paper provides a systematic review of domestic and international research advancements in this field， proposing an integrated optical and RF for cognitive software defined network architecture for SAGIN. It focuses on channel modeling methodologies for RF and FSO links applicable to heterogeneous space-air-ground environments， whilst conducting an in-depth analysis of core challenges including high-dynamic link precision alignment， intelligent allocation of heterogeneous resources， and robust transmission under extreme conditions. The paper then elaborates on key enabling technologies such as hybrid RF/FSO beam tracking， adaptive RF/FSO switching， parallel collaborative transmission， and scenario-specific link selection. Future research trends are also outlined， encompassing deep integration of intelligent algorithms， enhancement of cross-domain disturbance-resistant transmission， and holistic system performance optimization. Studies demonstrate that hybrid RF/FSO technology can significantly improve the overall performance of SAGIN. Nevertheless， its path towards large-scale application necessitates further in-depth research on cross-layer coordination mechanisms， dynamic resource management， and system-level performance evaluation.

With the rapid development of low-altitude intelligent networks (LAINs), the growing demand for data services poses significant challenges for the existing networks. At the same time, the airspace becomes increasingly complex due to the escalating count of low-altitude users. Although unmanned aerial vehicles (UAVs) carrying mobile base stations to provide communication services can effectively alleviate pressure on existing network infrastructure, they unfortunately face the dual challenge of sustaining reliable data transmission and guaranteeing UAV flight safety. Therefore, in this paper, we propose a collision-free UAVs communication model specifically designed for the hybrid low-altitude environment, incorporating both static and dynamic, as well as known and unknown obstacles. To efficiently support safe flight operations of UAVs, an artificial potential field (APF)-based collision probability map is constructed, enabling the UAVs to dynamically evaluate and avoid obstacles while maintaining high communication performance constrained by limited energy resources. To maximize energy efficiency in low-altitude environments with hybrid obstacles, an adaptive association multi-agent deep deterministic policy gradient (AA-MADDPG) algorithm is proposed to enable collaborative trajectory planning among multiple UAVs. Simulation results confirm that the proposed strategy enhances energy efficiency by 58.06% and reduces collision probability by 86.18%, achieving significant improvements in both communication performance and flight safety.

Due to the broadcasting characteristics of satellite-terrestrial integrated networks (STINs), security vulnerabilities have emerged as a critical concern requiring urgent mitigation strategies. Unlike traditional security methods, federated learning (FL) enables a large number of participants to collaborate without disclosing actual privacy data. Its potential as a framework that combines collaborative model training and covert payload transmission in STINs represents a significant research gap. This paper proposes FedSAT, a novel FL-based covert communication scheme for STINs, in which each participant in the FL process can utilize the shared learning protocol as a covert medium for transmitting arbitrary information in privacy-preserving framework. Our framework leverages the dual capabilities of FL for collaborative model training and covert payload embedding, utilizing Geostationary Earth Orbit (GEO) satellites and distributed terrestrial nodes to embed sensitive data within FL parameter updates. The system maintains model convergence accuracy while implementing strategic encryption to achieve robust sharing and transmission of payloads within the FL framework. Comprehensive simulation tests demonstrate the framework significant efficacy, achieving a 98.7% communication coverage for covert payload transmission under monitoring by low Earth orbit (LEO) surveillance satellites, with only a 0.8% decrease in model accuracy. This breakthrough achievement paves the way for a transformative paradigm in covert cross-domain communication for next-generation networks.

The growing demand for urban air mobility, drone logistics, and low-altitude aerial services has highlighted the need for intelligent and autonomous aerial networking solutions. Low Altitude Intelligent Networking (LAIN) emerges as a promising paradigm. Large Language Models (LLMs), with their capabilities in reasoning, language understanding, and task planning, have the potential to significantly improve the autonomy of unmanned aerial vehicle (UAV). However, cloud-based LLM access is often impractical in LAIN due to connectivity limitations and latency requirements. Deploying LLMs at the edge node offers a compelling alternative by enabling real-time responsiveness and onboard intelligence, but poses challenges such as limited computation, energy, and memory. In this paper, we present an offloading optimization problem for LLM inference in LAIN, aiming to maximize inference throughput. The problem is a variant of multidimensional knapsack problem, which is NP-hard. To address this NP-hard problem, we develop Dynamic Batching with Genetic Algorithm (DBGA) to address the multidimensional knapsack problem with constraints include communication and memory resources on edge server and UAV-specific latency and accuracy demands. Simulation results indicate that DBGA surpasses other batching benchmarks in request completion radio across diverse settings.

With the booming development of low-altitude intelligent networking (LAIN), free-space optical (FSO) based unmanned aerial vehicles (UAVs) communication offers a promising scheme to effectively address the challenge of the intense spectrum scarcity. However, due to the characteristics of FSO propagation, its performance is severely affected by the lowaltitude atmospheric conditions and complex airspace environment. To address these challenges, this work constructs an FSO assisted UAVs multi-hop relay system, where a multiagent double deep Q-network with prioritized experience replay (MADDQN-PER) approach is proposed for trajectory design, under the complex environment of low-altitude airspace such as the low-altitude obstacles and atmospheric visibility. To expound, the proposed scheme is expected to enhance the relay system capacity by intelligently adjusting UAVs' trajectories in the low-altitude airspace to maintain the multi-hop link stability. Simulation results demonstrate that the proposed scheme can effectively avoid time-varying low-altitude threat of varying severity while attaining about 10 % higher capacity when scaling from three to four UAVs.

Low-Earth-Orbit (LEO) constellations provide global coverage and low latency, but individual satellites have limited compute and offloading to ground adds hundreds of milliseconds of delay. Inter-Satellite Links (ISLs) enable collaborative inference to overcome these limits. Existing inter-satellite schemes focus on Convolutional Neural Networks (CNNs), but Vision Transformers (ViT) excel at high-resolution remote sensing through global self-attention, supporting small-object detection, fine-grained change monitoring, and robust occlusion handling. Deploying ViTs across a constellation is challenging due to large parameters and repeated key/value exchanges, imposing heavy bandwidth, synchronization, and scheduling demands. To tackle this issue, we propose ADPS-Sat (Adaptive Distributed Patch-Sequence Scheduling for Satellite-Edge ViT), the first practical system for collaborative ViT inference in LEO constellations. By decoupling NP-hard scheduling into patch enumeration-and-pruning and Particle Swarm Optimization(PSO)-driven sequence-parallel allocation within an alternating-optimization loop, ADPS-Sat adapts to dynamic task arrivals and link topologies. In a 4-satellite simulation using ViT-Base fine-tuned on the MillionAID dataset, ADPS improves average performance over the two state-of-the-art baselines by roughly 31.8%.

Hybrid free space optical (FSO) and radio frequency (RF) systems combine the high capacity of FSO links with the stability of RF links, providing a promising solution for unmanned aerial vehicle (UAV) networks. In such hybrid systems, reliable link switching is essential for maintaining stable UAV communication. In this paper, we develop an intelligent link switching scheme assisted by multi-source data prediction (ILS-MDP). By fusing visible light images, meteorological data, positional information, and signal measurements, the scheme supports link quality prediction under dynamic UAV channel conditions, thereby enabling timely switching decisions. To adapt to FSO channel fluctuations, the prediction horizon is dynamically adjusted based on a channel fluctuation index, while an integrated error feedback mechanism monitors real-time prediction errors and triggers timely re-prediction when significant deviations occur. Simulation results based on real-world meteorological data show that the scheme effectively reduces outage duration through proactive link switching and improves the average throughput compared to existing schemes.

In this work, a multiple waveguide pinching antenna system (PASS) assisted integrated sensing and communication (ISAC) system is proposed, where the base station (BS) is equipped with transmitting pinching antennas (PAs) and receiving uniform linear array (ULA) antennas. The PASS-transmitting-ULA-receiving (PTUR) BS transmits the communication and sensing signals through the PAs on waveguides and collects the echo sensing signals with the mounted ULA. Based on this configuration, a target sensing Cram & eacute;r-Rao Bound (CRB) minimization problem is formulated under communication quality-of-service (QoS) constraints, power budget constraint, and PA deployment constraints. To tackle the resulting non-convex problem, an alternating optimization (AO) framework is developed, which decomposes the problem into a digital beamforming sub-problem and a pinching beamforming sub-problem. The digital beamforming design is optimized via semidefinite relaxation (SDR), while the PA deployment is updated using penalty-based method. Simulation results demonstrate that: 1) the proposed PASS assisted ISAC framework achieves superior performance over benchmark schemes; and 2) the PASS assisted ISAC is less affected by stringent communication constraints compared to conventional MIMO-ISAC, and benefits from increasing the number of waveguides and PAs per waveguide.