Accurate interpretation of Notices To Airmen (NOTAMs) is critical for aviation safety, yet their condensed and cryptic language poses significant challenges to both manual and automated processing. Existing automated systems are typically limited to "Shallow Parsing," failing to extract the actionable intelligence needed for operational decisions. We formalize the complete interpretation task as "Deep Parsing," a dual-reasoning challenge requiring both dynamic knowledge grounding (linking the NOTAM to evolving real-world aeronautical data) and schema-based inference (applying static domain rules to deduce operational status). To tackle this challenge, we propose NOTAM-Evolve, a self-evolving framework that enables a Large Language Model (LLM) to autonomously master complex NOTAM interpretation. Leveraging a knowledge graph-enhanced retrieval module for data grounding, the framework introduces a crucial closed-loop learning process where the LLM progressively improves from its own outputs, minimizing the need for extensive human-annotated reasoning traces. In conjunction with this framework, we introduce a new benchmark dataset of 10,000 expert-annotated NOTAMs. Our experiments demonstrate that NOTAM-Evolve achieves a 30.4% absolute accuracy improvement over the base LLM, establishing a new state-of-the-art on the task of structured NOTAM interpretation.

To guarantee rational decision-making and safety of intelligent transportation systems and autonomous driving, existing vehicle trajectory prediction (VTP) methods extract spatial and temporal features from complex traffic environments to achieve accurate forecast results. However, they generally do not use the frequency-domain information inherently embedded in vehicle trajectory data, resulting in lower prediction accuracy. To solve this problem, we propose a joint spatio-temporal-frequency-aware feature fusion (STFA-FF) method for VTP. Firstly, an intention recognition network is proposed to integrate spatial features and temporal features to infer driving intentions with high precision. Secondly, to fully utilize frequency-domain features, we present a multi-scale frequency-domain feature extraction (MSFDFE) module to map vehicle trajectory data into the frequency domain, incorporate the high-frequency attenuation mask to suppress high-frequency noise, and deeply integrate short-term variations with long-term trends. Additionally, a frequency-domain channel selection (FDCS) module is proposed to dynamically select key frequency channels related to driving modes. Furthermore, a multi-domain feature fusion prediction network is proposed to process the spatial, temporal and frequency-domain features to generate the final trajectory prediction results. Finally, experimental results demonstrate that the proposed method significantly outperforms mainstream approaches in prediction accuracy and robustness.

A novel near-field integrated sensing and communications framework for secure unmanned aerial vehicle (UAV) networks with high time efficiency is proposed. A ground base station (GBS) with large aperture size communicates with one communication UAV (C-UAV) under the existence of one eavesdropping UAV (E-UAV), where the artificial noise (AN) is employed for both jamming and sensing purpose. Given that the E-UAV’s motion model is unknown at the GBS, we first propose a near-field localization and trajectory tracking scheme. Specifically, exploiting the variant Doppler shift observations over the spatial domain in the near field, the E-UAV’s three-dimensional (3D) velocities are estimated from echo signals. To provide the timely correction of location prediction errors, the extended Kalman filter (EKF) is adopted to fuse the predicted states and the measured ones. Subsequently, based on the real-time predicated location of the E-UAV, we further propose a joint GBS beamforming and C-UAV trajectory design scheme for maximizing the instantaneous secrecy rate, while guaranteeing the sensing accuracy constraint. To solve the resultant non-convex problem, an alternating optimization approach is developed, where the near-field GBS beamforming and the C-UAV trajectory design subproblems are iteratively solved by exploiting the successive convex approximation method. Finally, our numerical results unveil that: 1) the E-UAV’s 3D velocities and location can be accurately estimated in real time with our proposed framework by exploiting the near-field spherical wave propagation; and 2) the proposed framework achieves superior secrecy rate compared to benchmark schemes and closely approaches the performance when the E-UAV trajectory is perfectly known.

This article provides a comprehensive investigation into reconfigurable integrated sensing and communications (RISAC), an emerging paradigm designed to maximize the performance–cost tradeoff by exploiting the inherent spatial sparsity of multiple-input multiple-output (MIMO) arrays. Deviating from conventional static ISAC, RISAC adopts a cognitive “perception–action” cycle, enabling the adaptive reconfiguration of array geometries and beamforming weights in response to dynamic environmental feedback. Central to RISAC is the exploitation of two intertwined layers of degrees of freedom (DoFs): element-space sparsity via sparse MIMO array design and beam-space sparsity via hybrid beamforming (HBF). We further demonstrate that by synergistically co-designing these coupled DoFs, sparse MIMO HBF can rival the performance of fully digital systems when accounting for practical mutual coupling, at a significantly reduced hardware cost. This work analyzed both far-and near-field propagation regimes across various ISAC frameworks, including radar-centric, communication-centric, and joint co-design. In addition to downlink co-design, we also examine uplink coexistence via shared waveform design. Finally, this article outlines promising research directions, positioning RISAC as a critical evolution toward adaptive, hardware-efficient, and dual-functional systems.

Pinching-antenna systems (PASS) have emerged as a promising technology due to their ability to dynamically reconfigure wireless propagation environments. A novel PASS-based multi-user non-orthogonal multiple access (NOMA) framework is proposed by exploiting the waveguide-division (WD) transmission characteristic. Specifically, each NOMA user cluster is served by one dedicated waveguide, and the corresponding pinching beamforming is exploited to enhance the intra-cluster performance while mitigating the inter-cluster interference. Based on this framework, a sum-rate maximization problem is formulated for jointly optimizing power allocation, pinching beamforming, and user scheduling. To solve this problem, a two-step algorithm is developed, which decomposes the original problem into two subproblems. For the joint power allocation and pinching beamforming design, a penalty dual decomposition (PDD) algorithm is proposed to obtain the locally optimal solutions. Specifically, the coupling constraints are alleviated through augmented Lagrangian relaxation, and the resulting augmented Lagrangian (AL) problem is decomposed into four subproblems, which are solved by the block coordinate descent (BCD) method. For the user scheduling, a low-complexity matching algorithm is developed to solve the user-to-waveguide assignment problem. Simulation results demonstrate that 1) the proposed PASS-based NOMA framework under the WD transmission structure achieves significant sum-rate gain over conventional fixed-position antenna systems and orthogonal multiple access (OMA) scheme; and 2) the proposed matching-based user scheduling algorithm achieves near-optimal user-waveguide association with low computational complexity.

Pinching-antenna systems (PASS) represent an innovative advancement in flexible-antenna technologies, aimed at significantly improving wireless communications by ensuring reliable line-of-sight connections and dynamic antenna array reconfigurations. To employ multi-waveguide PASS in multi-user communications, three practical transmission structures are proposed, namely waveguide multiplexing (WM), waveguide division (WD), and waveguide switching (WS). Based on the proposed structures, the joint baseband signal processing and pinching beamforming design is studied for a general multi-group multicast communication system, with the unicast communication encompassed as a special case. A max-min fairness (MMF) problem is formulated for each proposed transmission structure, subject to the maximum transmit power constraint. For WM, to solve the highly-coupled and non-convex MMF problem with complex exponential and fractional expressions, a penalty dual decomposition (PDD)-based algorithm is invoked for obtaining locally optimal solutions. Specifically, the augmented Lagrangian relaxation is first applied to alleviate the stringent coupling constraints, which is followed by the block decomposition over the resulting augmented Lagrangian function. Then, the proposed PDD-based algorithm is extended to solve the MMF problem for both WD and WS. Furthermore, a low-complexity algorithm is proposed for the unicast case employing the WS structure, by simultaneously aligning the signal phases and minimizing the large-scale path loss at each user. Finally, numerical results reveal that: 1) the MMF performance is significantly improved by employing the PASS compared to conventional fixed-position antenna systems; 2) WS and WM are suitable for unicast and multicast communications, respectively; 3) the performance gap between WD and WM can be significantly alleviated when the users are geographically isolated.

A novel movable-element enabled simultaneously transmitting and reflecting surface (ME-STARS) communication system is proposed, where ME-STARS elements positions can be adjusted to enhance the degress-of-freedom for transmission and reflection. For each ME-STARS operating protocols, namely energy-splitting (ES), mode switching (MS), and time switching (TS), a weighted sum rate (WSR) maximization problem is formulated to jointly optimize the active beamforming at the base station (BS) as well as the elements positions and passive beamforming at the ME-STARS. An alternative optimization (AO)-based iterative algorithm is developed to decompose the original non-convex problem into three subproblems. Specifically, the gradient descent algorithm is employed for solving the ME-STARS element position optimization subproblem, and the weighted minimum mean square error and the successive convex approximation methods are invoked for solving the active and passive beamforming subproblems, respectively. It is further demonstrated that the proposed AO algorithm for ES can be extended to solve the problems for MS and TS. Numerical results unveil that: 1) the ME-STARS can significantly improve the WSR compared to the STARS with fixed position elements and the conventional reconfigurable intelligent surface with movable elements, thanks to the extra spatial-domain diversity and the higher flexibility in beamforming; and 2) the performance gain of ME-STARS is significant in the scenarios with larger number of users or more scatterers.

The large number of antennas in extremely large aperture array (ELAA) systems shifts the propagation regime of signals in wireless communication systems towards near-field spherical wave propagation, from beamforming to beamfocusing. The design of the two-dimensional beam codebook that contains both the angular and distance domains is challenging. To address this issue, we propose a reconfigurable intelligent surface (RIS)-assisted near-field beam training based on a novel multi-attention algorithm, which provides a fine-grained codebook with enhanced spatial resolution. Specifically, we transform the beam selection task into a location detection process, enabling more effective beam search. Experimental results unveil that the proposed method achieves beam selection accuracy up to 97% at signal-to-noise ratio (SNR) of 20 dB, and improves 10% over the baseline method at different SNRs.

The real-time near-field beamforming framework with the aided of 3D velocity sensing and localization for unmanned aerial vehicle (UAV) communications is proposed. Exploiting the variant Doppler shift over the spatial domain in the near field, the three-dimensional (3D) velocities are estimated with the echo signals. To provide timely correction of the location prediction errors with the estimated velocities, the extended Kalman filter (EKF) is adopted to fuse the predicted states and the estimated ones. Subsequently, the near-field beamforming can be conducted with the predicted locations of the UAV, thereby realizing zero-pilot and low-latency transmission. Numerical results unveil that, the proposed scheme can achieve the accurate tracking of the UAV's flying route.

The massive number of antennas in extremely large aperture array (ELAA) systems shifts the propagation regime of signals in internet of things (IoT) communication systems towards near-field spherical wave propagation. We propose a reconfigurable intelligent surfaces (RIS)-assisted beamfocusing mechanism, where the design of the two-dimensional beam codebook that contains both the angular and distance domains is challenging. To address this issue, we introduce a novel Transformer-based two-stage beam training algorithm, which includes the coarse and fine search phases. The proposed mechanism provides a fine-grained codebook with enhanced spatial resolution, enabling precise beamfocusing. Specifically, in the first stage, the beam training is performed to estimate the approximate location of the device by using a simple codebook, determining whether it is within the beamfocusing range (BFR) or the none-beamfocusing range (NBFR). In the second stage, by using a more precise codebook, a fine-grained beam search strategy is conducted. Experimental results unveil that the precision of the RIS-assisted beamfocusing is greatly improved. The proposed method achieves beam selection accuracy up to 97% at signal-to-noise ratio (SNR) of 20 dB, and improves 10% to 50% over the baseline method at different SNRs.

The Vehicle Routing Problem (VRP) is a classic optimization problem with diverse real-world applications. The neighborhood search has emerged as an effective approach, yielding high-quality solutions across different VRPs. However, most existing studies exhaustively explore all considered neighborhoods with a pre-fixed order, leading to an inefficient search process. To address this issue, this paper proposes a Learning-aided Neighborhood Search algorithm (LaNS) that employs a cutting-edge multi-agent reinforcement learning-driven adaptive operator/neighborhood selection mechanism to achieve efficient routing for VRP. Within this framework, two agents serve as high-level instructors, collaboratively guiding the search direction by selecting perturbation/improvement operators from a pool of low-level heuristics. Furthermore, to equip the agents with comprehensive information for learning guidance knowledge, we have developed a new informative state representation. This representation transforms the spatial route structures into an image-like tensor, allowing us to extract spatial features using a convolutional neural network. Comprehensive evaluations on diverse VRP benchmarks, including the capacitated VRP (CVRP), multi-depot VRP (MDVRP) and cumulative multi-depot VRP with energy constraints, demonstrate LaNS's superiority over the state-of-the-art neighborhood search methods as well as the existing learning-guided neighborhood search algorithms.

A continuous aperture array (CAPA)-based secure communication system is investigated, where a base station (BS) equipped with a CAPA transmits signals to a legitimate user under the existence of an eavesdropper. For improving the secrecy performance, the artificial noise (AN) is employed at the BS for the jamming purpose. We aim at maximizing the secrecy rate by jointly optimizing the information-bearing and AN source current patterns, subject to the maximum transmit power constraint. To solve the resultant non-convex integral-based functional programming problem, a channel subspace-based approach is first proposed via exploiting the result that the optimal current patterns always lie within the subspace spanned by all users’ channel responses. Then, the intractable CAPA continuous source current pattern design problem with an infinite number of optimization variables is equivalently transformed into the channel-subspace weighting factor optimization problem with a finite number of optimization variables. A penalty-based successive convex approximation method is developed for iteratively optimizing the finite-size weighting vectors. To further reduce the computational complexity, we propose a two-stage source current patterns design scheme. Specifically, the information-bearing and AN patterns are first designed using the maximal ration transmission (MRT) and zero-forcing (ZF) transmission, respectively. Then, the remaining power allocation is addressed via the one-dimensional search method. Numerical results unveil that 1) the CAPA brings in significant secrecy rate gain compared to the conventional discrete multiple-input multiple-output (MIMO); 2) the proposed channel subspace-based algorithm outperforms the conventional Fourier-based approach, while sustaining much lower computational complexity; and 3) the two-stage ZF-MRT approach has negligible performance loss for the large transmit power regime.

Probabilistic aircraft trajectory models in the terminal area that reflect real-world distributions can significantly facilitate conflict detection, performance analyses, and risk assessments. However, due to the inherent uncertainties in air traffic, complex spatiotemporal correlations within terminal area, and the influence of diverse weather conditions, modeling these distributions and generating realistic trajectories pose substantial challenges. In this paper, we present a diffusion model-based method to learn the distribution of aircraft trajectories in the terminal area, enabling the generation of high-quality trajectories that resemble real data distributions. This is achieved by effectively combining the generative capability of diffusion models with the ability of extracting spatiotemporal features embedded in real trajectories. Specifically, we propose an airplane trajectory diffusion network structure, which integrates a UNet deep neural network to capture multi-level noise estimation and accurately model the uncertainty inherent in trajectory data. Additionally, we employ a conditional generation module that incorporates meteorological information, allowing the model to learn the correlation between weather conditions and trajectory distributions. Experiments with real-world terminal-area datasets demonstrate that our model can generate realistic trajectories that closely resemble the actual distribution of terminal area flight paths. Comparative results present improvements over existing methods across various evaluation metrics.

This paper deals with sideslip angle estimation problems of autonomous ground vehicles that repeatedly perform the specific tasks in the absence of model knowledge for their lateral dynamics. By designing appropriate estimators, the equivalence between estimator auxiliary input synthesis and output feedback stabilization along the iteration axis is established. Moreover, we propose an innovative data-based output feedback stabilization framework that leverages insufficient sampled data to formulate an output feedback controller without the need of identification. To be specific, with the application of some helpful linear matrix inequality (LMI) techniques, the data-based synthesis of required output feedback controller is transformed into solving the equivalent LMI conditions. By employing the proposed data-based estimation strategy and partial lateral dynamics information of ground vehicles, accurate estimation of sideslip angles over the entire estimation duration can be achieved even in the presence of disturbances. Experiments on an Ackermann steering intelligent vehicle are provided to demonstrate the effectiveness of the proposed estimation strategy.

In this brief, we investigate the approximation theory (AT) of Bayesian recurrent neural network (BRNN) for stochastic time series forecasting (TSF) from a probabilistic standpoint. Due to the cumulative dependencies present in stochastic time series, which are incompatible with the recurrent structure of BRNN and further complicate the analysis of AT, we first perform marginalization and transform the time series into a probabilistically equivalent latent variable model (LVM). Subsequently, we analyze the AT by evaluating the approximation error between the output mean of BRNN and that of the LVM, which are derived through Taylor expansion-based uncertainty propagation and distribution parameterization, respectively. Finally, leveraging the Khinchin's law of large numbers, we study the convergence in probability of the sampling-based training algorithm, i.e., Bayes by Backprop (BBB), and prove that increasing the number of Monte Carlo samples in BBB leads to a convergence probability approaching one. Numerical simulations are conducted to demonstrate the validity of our results.

A novel time-efficient framework is proposed for improving the robustness of a broadband multiple-input multiple-output (MIMO) system against unknown interference under rapidly-varying channels. A mean-squared error (MSE) minimization problem is formulated by optimizing the beamformers employed. Since the unknown interference statistics are the premise for solving the formulated problem, an interference statistics tracking (IST) module is first designed. The IST module exploits both the time- and spatial-domain correlations of the interference-plus-noise (IPN) covariance for the future predictions with data training. Compared to the conventional signal-free space sampling approach, the IST module can realize zero-pilot and low-latency estimation. Subsequently, an interference-resistant hybrid beamforming (IR-HBF) module is presented, which incorporates both the prior knowledge of the theoretical optimization method as well as the data-fed training. Taking advantage of the interpretable network structure, the IR-HBF module enables the simplified mapping from the interference statistics to the beamforming weights. The simulations are executed in high-mobility scenarios, where the numerical results unveil that: 1) the proposed IST module attains promising prediction accuracy compared to the conventional counterparts under different snapshot sampling errors; and 2) the proposed IR-HBF module achieves lower MSE with significantly reduced computational complexity.

This article is aimed at developing novel safe iterative learning methods to deal with the high-precision attitude tracking problems of rigid bodies subjected to both nonconvex orientation constraints and iteration-dependent uncertainties. A “reactive exploration” strategy involving a dual-component mechanism is posed to realize safe iterative learning. The first component, named the learning mechanism, adeptly adjusts the learning intervals’ lengths and learns the information about the unmodeled dynamics and external disturbances. The second component, named the safety mechanism, handles the problem of multiple nonconvex orientation constraints. The two mechanisms operate independently, avoiding any potential coupling problems between them. Moreover, thanks to constructing two energy functions based on the auxiliary error information, the orientation constraint satisfaction and perfect tracking can be rigorously verified, regardless of the iteration-dependent learning intervals and the absence of the persistent full-learning assumption. In particular, the nonconvex orientation constraints can be time-iteration-dependent. Two simulation tests are provided to validate the effectiveness of the proposed safe iterative learning method for rigid spacecraft in a Sun-synchronous orbit.Note to Practitioners—Attitude tracking of rigid spacecraft or unmanned aerial/surface vehicles generally requires both safe operation and high precision for some specific periodical tasks, such as the repetitive sensing mission of satellites equipped with star sensors which are prevented from pointing to some undesired directions. With iterative learning control (ILC), it becomes possible to extract the useful information from previous operations and achieve perfect attitude tracking. However, conventional ILC is difficult to apply to the repetitive attitude tracking tasks when nonconvex orientation constraints exist. This work provides new insights into the “repetitive property”, leading to the development of safe ILC based on the “reactive exploration” strategy. This strategy resolves the coupling issue between the learning mechanism and the safety mechanism, which simplifies the controller design for practitioners. Moreover, perfect attitude tracking can be achieved despite the presence of time-iteration-dependent nonconvex constraints and iteration-dependent learning intervals. A novel composite energy function-based analytical method and numerical simulations are introduced to demonstrate the effectiveness of the proposed safe ILC method.

Understanding surface congestion is essential for improving taxiing efficiency and reducing carbon emissions in busy airports. Diverging from the traditional input-output and dynamics analysis, we propose a novel end-to-end framework to study the complete dynamic process of airport surface congestion and recovery. This framework employs a stochastic hybrid system to model multi-timescale dynamics, integrating continuous states and discrete modes of surface operations under uncertainty. First, the probabilistic reachable set for the input-output state is computed via a chance-constrained optimization program to represent the relationship between the number of aircraft taxiing out and the departure throughput. Next, the discrete modes are divided based on taxiing efficiency and traffic load, utilizing tailored congestion contour regression and density-based clustering, respectively. Finally, the transition trajectory incorporating mode information is constructed to depict the complete process from congestion formation to subsequent recovery, followed by employing an unsupervised algorithm to identify representative patterns. The proposed framework is verified using two years of real-world datasets from Chengdu Shuangliu International Airport, China. Experimental results demonstrate the superiority of our approach compared with the baselines. Moreover, this work also reveals some intriguing findings, such as the diverse multi-timescale dynamical phenomena, and their implications for practical airport surface operations.

Due to the significance of air traffic delay propagation in the operational robustness of air transport systems, it has recently received increased attention from both industry and academia. The purpose of delay propagation analysis is to capture the dynamic traveling trajectories of root delays in air traffic networks. Few studies have investigated delay propagation while taking consideration of temporal context information, leading to incomplete traveling trajectories of root delays. In this paper, a novel systematic framework based on temporal causal inference is proposed to model delay propagation in airport networks. More specifically, considering the lagged nature caused by the transition time in delay propagation, a fully-connected delay propagation network based on transfer entropy is developed. Additionally, a causal biased random walk is embedded to explore the temporal cascading effect of root delays in air transport systems and to generate delay propagation trees for each airport. Extensive experiments on a real-world dataset indicate that our framework is able to effectively model the dynamic evolution of air traffic delays in an airport network with acceptable performance. This paper also presents a real-world case study of the Chinese airport network, which reveals that the traveling trajectories of air traffic delays differ significantly at various daily delay levels and airport throughput.

Multiple object tracking plays a crucial role in intelligent transportation systems. Due to the varying size, fast motion, and occlusion of traffic objects, multiple object tracking in complex traffic scenes is prone to low tracking accuracy and tracking fragmentation. To solve these problems, numerous tracking methods have been proposed based on object discrimination feature. However, these methods neglect the guiding prior role of historical tracking information for detection, making them not applicable to more complex scenes, such as extremely small, fast-moving, and severely obscured objects. In this paper, we propose an Interactively Motion-assisted Network (IMANet) for multiple object tracking in complex traffic scenes. First, to capture the object motion patterns from historical frames, an object motion modeling module considering camera movement is proposed, which particularly has prominent advantages on videos obtained by moving cameras. Next, a multi-scale fusion detection and embedding module is designed to incorporate historical motion information, thereby improving detection performance. Finally, multiple object tracking can be achieved by associating objects detected in different frames based on detection and embedding results. The proposed method combines the detection and tracking in an interactive way, where detection performance is facilitated using historical information provided by the tracking module, and better detection in turn enhances the tracking. Several real-world traffic examples are used to illustrate the performance of the proposed method in both detecting and tracking traffic objects. The results demonstrate that the proposed method outperforms the state-of-the-art methods, especially in complex surveillance videos with varying sizes and occlusions.

With the rapid rise of massive multi-modal Internet data, air crisis event recognition plays a significant role in accident information management. A key feature of this work is the open-world setting, where the new events can be detected via the model trained from the known events. A scenario-guided Transformer-enabled multi-modal unknown air crisis event classification is proposed. Firstly, we introduce a memory-augmented feature representation module to improve the cross-modal feature fusion in the basic Transformer network, where the textual and image features of the air crisis events are extracted through the pre-trained models. Then, a scenario-guided mechanism is proposed to pivot the pseudo event simulation to approximate the distribution of unknown events effectively. Specifically, an end-to-end scenario attention with a cross-event mask module is presented to select the valid samples of pseudo events and filter out the invalid ones. Finally, the unknown event classifier is designed to classify the known classes and recognize the unknown events simultaneously. Moreover, a specialized multi-modal dataset on air crisis events is proposed as a benchmark, named AirCrisisMMD. The extensive experiments are performed on the AirCrisisMMD and CrisisMMD datasets, where the latter is the publicly available multi-modal crisis event dataset. The results verify the superior performance boost of the proposed method compared with the highly related state-of-the-art baselines.

This article focuses on exploring a class of Lyapunov analysis approaches to deal with the convergence problems on second-order signed networks (SOSNs) under arbitrary strongly connected directed topologies. A new class of Laplacian potentials is first proposed for SOSNs by exploiting the properties of Laplacian matrices. Then the relation between convergence behaviors of all agents and those of Laplacian potentials can be disclosed, which makes it possible to solve the convergence issues of SOSNs from the viewpoint of the Lyapunov stability theory even though the weight-balanced condition is not satisfied. Furthermore, the proposed Laplacian potential can be leveraged to deal with the convergence problems of distributed averaging for SOSNs. It is shown that the signed-average consensus objective is reached under the structurally balanced signed digraphs by designing a distributed control protocol according to the proposed Laplacian potential. Additionally, simulation examples are given to demonstrate the validity of our potential-based distributed control results.

In the realm of data-driven adaptive iterative learning control (AILC), the emphasis in designing and analyzing control schemes mainly concentrates on discrete-time systems, while fewer results are developed for the more common continuous-time plants. To overcome this limitation, a practical sampled-data AILC (SDAILC) is developed for continuous-time nonaffine nonlinear plants. A sampled-data iterative dynamic linearization (SDIDL) method is devised to build the dynamic connection between input and output (I/O) data throughout different iterations. On this basis, the SDAILC method, including a sampled-data parameter estimation algorithm and a learning control law, is proposed by utilizing optimization-based design. In SDAILC, the sampling period is treated as a parameter to compensate for its influence on the control performance, and an error feedback is naturally involved, improving the robustness against uncertainties and the closed-loop stability of the plant. Notably, SDAILC is a data-driven approach independent of model information. The validity of SDAILC is proved mathematically and demonstrated by simulations.

With the emergence of fifth-generation (5G) technology, the air-to-ground (ATG) communication system based on 5G public mobile communication technology makes it possible to provide data services for in-flight communication. Customer premises equipment (CPE) is connected to ATG base stations to provide network access for user devices in-cabin. However, the handover authentication performed by CPEs during a handover between ATG base stations poses security risks and incurs a lot of overhead. Furthermore, frequent handovers between base stations and the limited computational resources of the CPE make the protection of security properties even more challenging. In this paper, we propose a lightweight group pre-handover authentication scheme for aviation 5G ATG networks. By leveraging the predictability of flight paths, all CPEs on the same aircraft can complete handover authentication before arriving at the next base station, and handover authentication delay can be ignored, providing seamless communication services for user devices in the cabin. The scheme utilizes the extended Chebyshev chaotic map and symmetric encryption technology to reduce computational overhead and adapt to the limited computing resources of CPE. Security and performance analysis show that our scheme achieves lightweight and efficiency while ensuring security performance and outperforms other relevant schemes.

This article aims at exploring the dynamic behaviors of signed networks under the mixed static and dynamic control protocols, which reflect the existence of two classes of communication channels. An extended leader-follower framework admitting multiple dynamic leaders is established to identify the roles of all nodes in signed networks, depending on the union of two related signed digraphs. It is shown that bipartite containment tracking is achieved for signed networks despite any topology conditions. To be specific, every leader group realizes modulus consensus and the leaders dominate the dynamic evolutions of signed networks such that all followers converge within the bounded zone spanned by the leaders' converged states and their symmetric states. Furthermore, conditions on the zero convergence of dynamic control inputs are exploited, together with those on the (interval) bipartite consensus of signed networks. Simulation examples are given to demonstrate the convergence behaviors of signed networks with respect to the mixed static and dynamic control protocols.

In learning systems, high operation precision is often a desirable objective for the algorithm design. Though centralized algorithms are generally adopted, they are subjected to restrictive hypotheses on the learning systems. To overcome this challenging problem, we aim to propose some distributed learning algorithms that focus specifically on achieving the perfect tracking tasks for iterative learning control (ILC) systems. By noting the equivalent relation between the perfect tracking problem of ILC systems and the solving problem of linear algebraic equations (LAEs), we first present an observer-based distributed learning algorithm to solve LAEs, where a multiagent system is constructed with every agent being only required to access some partial information for LAEs. The distributed learning algorithm benefits from integrating both observer-based design and consensus-based design ideas such that for any solvable LAE, all agents can agree on a common solution of it under any initial conditions of agents, regardless of whether it has a unique solution or not. Then, with the distributed learning algorithm for LAEs, we further develop two classes of distributed learning control algorithms for ILC systems, which establish the perfect tracking objective in the presence of the trackable desired output even without using the basic relative degree condition that is generally imposed for conventional ILC.

A reconfigurable intelligent surface (RIS) aided air-to-ground uplink non-orthogonal transmission framework is investigated for next generation multiple access. Occupying the same spectrum resource, unmanned aerial vehicle (UAV) users and ground users (GUs) are connected to terrestrial cellular networks via the uplink non-orthogonal multiple access (NOMA) protocol. As the flight safety is important for employing UAVs in civil airspace, the collision avoidance mechanism has to be considered during the flight. Therefore, a joint optimization problem of the UAV trajectory design, RIS configuration, and uploading power control is formulated for maximizing the network sum rate, while ensuring the UAV’s fight safety and satisfying the minimum data rate requirements of both the UAV and GU. The resultant problem is a sequential decision making one across multiple coherent time slots. Besides, the unknown locations of obstacles bring uncertainties into the decision making process. To tackle this challenging problem, a sample-efficient deep reinforcement learning (DRL) algorithm is proposed to optimize the UAV trajectory, RIS configuration, and power control simultaneously. Moreover, considering the ambiguous uncertainties in the environment, a distributionally robust DRL algorithm is further proposed to provide the worst-case performance guarantee. Numerical results demonstrate that the two proposed DRL algorithms outperform the conventional ones in terms of learning efficiency and robustness. It is also shown that the network sum rate is significantly improved by the proposed RIS-NOMA scheme compared to the conventional RIS-orthogonal multiple access (OMA) scheme and the case where no RIS is deployed.

A novel air-to-ground communication paradigm is conceived, where an unmanned aerial vehicle (UAV)-mounted base station (BS) equipped with multiple antennas sends information to multiple ground users (GUs) with the aid of a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS). In contrast to the conventional RIS whose main function is to reflect incident signals, the STAR-RIS is capable of both transmitting and reflecting the impinging signals from either side of the surface, thereby leading to full-space 360 degree coverage. However, the transmissive and reflective capabilities of the STAR-RIS require more complex transmission/reflection coefficient design. Therefore, in this work, a sum-rate maximization problem is formulated for the joint optimization of the UAV’s trajectory, the active beamforming at the UAV, and the passive transmission/reflection beamforming at the STAR-RIS. This cutting-edge optimization problem is also subject to the UAV’s flight safety, to the maximum flight duration constraint, as well as to the GUs’ minimum data rate requirements. Given the unknown locations of obstacles prior to the UAV’s flight, we provide an online decision making framework employing reinforcement learning (RL) to simultaneously adjust both the UAV’s trajectory as well as the active and passive beamformer. To enhance the system’s robustness against the associated uncertainties caused by limited sampling of the environment, a novel “distributionally-robust” RL (DRRL) algorithm is proposed for offering an adequate worst-case performance guarantee. Our numerical results unveil that: 1) the STAR-RIS assisted UAV communications benefit from significant sum-rate gain over the conventional reflecting-only RIS; and 2) the proposed DRRL algorithm achieves both more stable and more robust performance than the state-of-the-art RL algorithms.

Signed networks admitting antagonistic interactions among agents may polarize, cluster, or fluctuate in the presence of time-varying communication topologies. Whether and how signed networks can be stabilized regardless of their sign patterns is one of the fundamental problems in the network system control areas. To address this problem, this paper targets at presenting a self-appraisal mechanism in the protocol of each agent, for which a notion of diagonal dominance degree is proposed to represent the dominant role of agent's self-appraisal over external impacts from all other agents. Selection conditions on diagonal dominance degrees are explored such that signed networks in the presence of directed time-varying topologies can be ensured to achieve the uniform asymptotic stability despite any sign patterns. Further, the established stability results can be applied to achieve bipartite consensus tracking of time-varying signed networks and realize state-feedback stabilization of time-varying systems. Simulations are implemented to verify our uniform asymptotic stability results for directed time-varying signed networks.

Flight delay prediction has recently gained growing popularity due to the significant role it plays in efficient airline and airport operation. Most of the previous prediction works consider the single-airport scenario, which overlooks the time-varying spatial interactions hidden in airport networks. In this paper, the flight delay prediction problem is investigated from a network perspective (i.e., multi-airport scenario). To model the time-evolving and periodic graph-structured information in the airport network, a flight delay prediction approach based on the graph convolutional neural network (GCN) is developed in this paper. More specifically, regarding that GCN cannot take both delay time-series and time-evolving graph structures as inputs, a temporal convolutional block based on the Markov property is employed to mine the time-varying patterns of flight delays through a sequence of graph snapshots. Moreover, considering that unknown occasional air routes under emergency may result in incomplete graph-structured inputs for GCN, an adaptive graph convolutional block is embedded into the proposed method to expose spatial interactions hidden in airport networks. Through extensive experiments, it has been shown that the proposed approach outperforms benchmark methods with a satisfying accuracy improvement at the cost of acceptable execution time. The obtained results reveal that deep learning approach based on graph-structured inputs have great potentials in the flight delay prediction problem.

Air traffic flow management (ATFM) aims to facilitate the utilization of airspace and airport resources and is critical in air transportation systems. During the past decades, several challenging problems have arisen from this domain and attracted intensive studies. This paper addresses the problem of alleviating the airspace congestion and reducing the flight delays in ATFM simultaneously. We formulate this problem as a multi-objective air traffic network flow optimization (MATNFO) problem. In this MATNFO model, comprehensive ATFM actions, for instance, ground-holding, airborne-holding, rerouting, and speed control, are considered. Meanwhile, a systematic approach, namely route and time-slot assignment (RTA) algorithm, is developed to solve the MATNFO problem. The idea of divide-and-conquer is embedded in the algorithm by sequentially applying both route searching module and time refinement module. Furthermore, for the sake of efficiency, a pre-selection operator is proposed as one heuristic strategy to identify promising solutions and reduce the search space by defining a sector equilibrium metric. Experiments on real data of the Chinese airspace show that the RTA algorithm outperforms an existing competitor and three related multi-objective evolutionary algorithms. In addition, RTA is competent for high-quality real-time air traffic network flow assignment.

The air-based information network of the Space-Air-Ground Integrated Network has the distinct characteristics of heterogeneous, time-varying, distributed and self-organized, which bring not only new challenges of node mobility model, dynamic network grouping and interconnection and intercommunication of heterogeneous networks, but also higher requirements of network security. Therefore, selecting an efficient and safe communication link is critical when there may not be fixed rules. In this article, we build a model of the air-based information network, and use the method of dynamic programming to select the most efficient communication link by minimizing the energy consumption in the communication model. In the communication model, energy consumption is associated with the security level of the communication link. The experiments show that the presented algorithms can effectively reduce the total cost while satisfying security constraints.

The ever-growing air traffic flow has brought about great challenges to balance the airspace congestion and air traffic demands. This fact sparks numerous studies on Network-wide Flights Planning Optimization (NFPO) which aims to reconcile the contradiction between flight delay cost and airspace congestion by optimizing the pre-strategic flight plans from a network-wide point of view. In consideration of bi-objective and large-scale characteristics of the NFPO problem, this paper proposes a multi-objective Memetic Algorithm with Rerouting Meme (MARM) that incorporates an evolutionary global search framework with a problem-specific meme ulocal search operator. With the idea of heuristically reducing the interactions among flight trajectories to decongest the airspace, the Trajectories Correlation (TC) is defined as key network-wide knowledge and is applied to design the critical Rerouting Meme (RM). Additionally, to balance the ability of exploitation and exploration, the idea of simulated heating configuration setting is adopt for RM to integrate with the global search. Extensive empirical studies conducted on real large-scale traffic data of China air traffic network and flight plans support that MARM is beneficial to the NFPO problem via showing the improvement on effectiveness.

The large-scale Crossing Waypoints Location Problem (CWLP) is a crucial problem in the design of Air Route Network (ARN). CWLP is fully non-separable and non-differentiable, and thus traditional algorithms can hardly deal with it. This paper proposes an algorithm named Cooperative Co-evolution with Weighted Random Grouping (CCWR) to tackle it. CCWR employs the weighted random (WR) grouping strategy, which is specifically designed for CWLP, to divide the large-scale Crossing Waypoints (CWs) into small sub-groups and an Evolutionary Algorithm (EA) to solve the smaller scale CWs location problem in each sub-group. Experiments on the database of the ARN in China have been carried out to evaluate the performance of CCWR. The results showed that CCWR is superior to a number of state-of-the-art algorithms, and the advanced performance of CCWR is mainly due to the WR grouping strategy.