Search Results (133)

Unmanned platforms such as unmanned aerial vehicles, unmanned ground vehicles, and autonomous underwater vehicles often face challenges of data, device, and model heterogeneity when performing collaborative data processing tasks. Existing research does not simultaneously address issues from these three aspects. To address this issue, this study designs an unmanned platform cluster architecture inspired by the cloud-edge-end model. This architecture integrates federated learning for privacy protection, leverages the advantages of distributed model training, and utilizes edge computing’s near-source data processing capabilities. Additionally, this paper proposes a federated edge intelligence method (DSIA-FEI), which comprises two key components. Based on traditional federated learning, a data sharing mechanism is introduced, in which data is extracted from edge-side platforms and placed into a data sharing platform to form a public dataset. At the beginning of model training, random sampling is conducted from the public dataset and distributed to each unmanned platform, so as to mitigate the impact of data distribution heterogeneity and class imbalance during collaborative data processing in unmanned platforms. Moreover, an intelligent model aggregation strategy based on similarity measurement and loss gradient is developed. This strategy maps heterogeneous model parameters to a unified space via hierarchical parameter alignment, and evaluates the similarity between local and global models of edge devices in real-time, along with the loss gradient, to select the optimal model for global aggregation, reducing the influence of device and model heterogeneity on cooperative learning of unmanned platform swarms. This study carried out extensive validation on multiple datasets, and the experimental results showed that the accuracy of the DSIA-FEI proposed in this paper reaches 0.91, 0.91, 0.88, and 0.87 on the FEMNIST, FEAIR, EuroSAT, and RSSCN7 datasets, respectively, which is more than 10% higher than the baseline method. In addition, the number of communication rounds is reduced by more than 40%, which is better than the existing mainstream methods, and the effectiveness of the proposed method is verified. Full article

The efficient management of urban parking systems has emerged as a pivotal issue in today’s smart cities, where increasing vehicle populations strain limited parking infrastructure and challenge sustainable urban mobility. Aligned with the United Nations 2030 Agenda for Sustainable Development and the strategic goals of smart city planning, this study presents a sustainability-driven, multiagent simulation-based framework to model, analyze, and optimize smart parking dynamics in congested urban settings. The system architecture integrates ground-level IoT sensors installed in parking spaces, enabling real-time occupancy detection and communication with a centralized system using low-power wide-area communication protocols (LPWAN). This study introduces an intelligent parking guidance mechanism that dynamically directs drivers to the nearest available slots based on location, historical traffic flow, and predicted availability. To manage real-time data flow, the framework incorporates message queuing telemetry transport (MQTT) protocols and edge processing units for low-latency updates. A predictive algorithm, combining spatial data, usage patterns, and time-series forecasting, supports decision-making for future slot allocation and dynamic pricing policies. Field simulations, calibrated with sensor data in a representative high-density urban district, assess system performance under peak and off-peak conditions. A comparative evaluation against traditional first-come-first-served and static parking systems highlights significant gains: average parking search time is reduced by 42%, vehicular congestion near parking zones declines by 35%, and emissions from circling vehicles drop by 27%. The system also improves user satisfaction by enabling mobile app-based reservation and payment options. These findings contribute to broader sustainability goals by supporting efficient land use, reducing environmental impacts, and enhancing urban livability—key dimensions emphasized in sustainable smart city strategies. The proposed framework offers a scalable, interdisciplinary solution for urban planners and policymakers striving to design inclusive, resilient, and environmentally responsible urban mobility systems. Full article

When hypersonic vehicles fly in near space, the flow field near the optical window leads to light displacement, jitter, blurring, and energy attenuation of the star sensor. This ultimately affects the imaging quality and navigation accuracy. In order to investigate the impact of aerodynamic optical effects on imaging, the fourth-order Runge–Kutta and the fourth-order Adams–Bashforth–Moulton (ABM) predictor-corrector methods are used for ray tracing on the density data. A comparative analysis of the imaging quality results from the two methods reveals their respective strengths and limitations. The influence of the optical system is included in the image quality calculations to make the results more representative of real data. The effects of altitude, velocity, and angle of attack on the imaging quality are explored when the optical window is located at the tail of the vehicle. The results show that altitude significantly affects imaging results, and higher altitudes reduce the impact of the flow field on imaging quality. When the optical window is located at the tail of the vehicle, the relationship between velocity and offset is no longer simply linear. This research provides theoretical support for analyzing the imaging quality and navigation accuracy of a star sensor when a vehicle is flying at hypersonic speeds in near space. Full article

Stellar refraction autonomous navigation provides a promising alternative for cross-domain vehicles, particularly in near-space environments where traditional inertial and satellite navigation methods face limitations. This study develops a stellar refraction navigation system that utilizes stellar refraction angle observations and the Implicit Unscented Kalman Filter (IUKF) for state estimation. A representative orbit with altitudes ranging from 60 km to 200 km is designed to simulate cross-domain flight conditions. The navigation performance is analyzed under varying conditions, including orbital altitude, as well as star sensor design parameters, such as limiting magnitude, field of view (FOV) value, and measurement error, along with different sampling intervals. The simulation results show that increasing the limiting magnitude from 5 to 8 reduced the position error from 705.19 m to below 1 m, with optimal accuracy reaching 0.89 m when using a 20° × 20° field of view and a 3 s sampling interval. In addition, shorter sampling intervals improved accuracy and filter stability, while longer intervals introduced greater integration drift. When the sampling interval reached 100 s, position error grew to the kilometer level. These findings validate the feasibility of using stellar refraction for autonomous navigation in cross-domain scenarios and provide design guidance for optimizing star sensor configurations and sampling strategies in future near-space navigation systems. Full article

This paper presents a distributed adaptive formation control strategy for a multiple near-space vehicles (NSVs) system operating under unknown input constraints and external disturbances. In challenging near-space environments, the control system must address not only model uncertainties and parameter variations but also accommodate the input limitations of actuators. To address these challenges, we design an adaptive distributed formation control strategy for vehicle formation that relies exclusively on relative attitude information. This approach is grounded in the principles of angle rigidity formation theory, which has not previously been applied in the near-space vehicle domain. The aim of the adaptive formation control strategy is to maintain the desired formation shape for the near-space vehicles (NSVs) system with external disturbances, actuator dead zones, and saturation. In addition, neural networks are employed to approximate the inherent nonlinear uncertainties within the NSV models. An adaptive estimation technique is concurrently included to address parameter variations and to alleviate the impact of external disturbances, actuator dead zones, and saturation effects. Finally, a Lyapunov-based analysis is used to rigorously demonstrate the stability of the NSV formation system. The simulation results validate the effectiveness and robustness of the proposed control strategy in uncertain environments. Full article

Blades are widely used in the engines of aerospace vehicles, fans of near-space aerostat, and other equipment, and they are the key to completing energy conversion and pressure adjustment of the capsule. Blade tip timing (BTT) is the most cost-efficient approach for the monitoring of blades. The reliability and validity of BTT is mainly investigated through numerical simulation and experimental verification. However, not all researchers are able to carry out the expensive and time-consuming task of rotating the blade test bench and its monitoring systems. Therefore, a good and easily understood simulator is necessary. In this paper, an effective BTT simulation model that is capable of considering various uncertainties such as installation errors, probe accuracy, sampling clock frequency, speed fluctuations, and mistuning is presented. A blade multi-harmonic vibration model is also presented, which is not only easy to implement but also simplifies the solution of dynamic equations. Also, the simulation results show that the proposed model is accurate and consistent with the experimental results. This will help researchers to achieve an improved understanding of BTT and form the basis for conducting research in related areas in a short period of time. Full article

High-density cities have obvious characteristics of compact urban spatial form and intensive land use in terms of spatial environment, and have always been a topic of academic focus. As a typical coastal historical district, the Macau Peninsula pier district (mainly the Macau Inner Harbour) has a high building density and a low average street width, forming a vertical coastline development model that directly converses with the ocean. This area is adjacent to Macau’s World Heritage Site and directly related to the Marine trade functions. The distribution pattern of cultural heritage linked by the ocean has strengthened Macau’s unique positioning as a node city on the Maritime Silk Road. This text is based on the theory of urban development, integrates spatial syntax and POI analysis techniques, and combines the theories of waterfront regeneration, high-density urban form and post-industrial urbanism to integrate and deepen the theoretical framework, and conduct a systematic study on the urban spatial characteristics of the coastal area of the Macau Peninsula. This study found that (1) Catering and shopping facilities present a dual agglomeration mechanism of “tourism-driven + commercial core”, with Avenida de Almeida Ribeiro as the main axis and radiating to the Ruins of St. Paul’s and Praça de Ponte e Horta, respectively. Historical blocks and tourist hotspots clearly guide the spatial center of gravity. (2) Residential and life service facilities are highly coupled, reflecting the spatial logic of “work-residence integration-service coordination”. The distribution of life service facilities basically overlaps with the high-density residential area, forming an obvious “living circle + community unit” structure with clear spatial boundaries. (3) Commercial and transportation facilities form a “functional axis belt” organizational structure along the main road, with the Rua das Lorchas—Rua do Almirante Sérgio axis as the skeleton, constructing a “functional transmission chain”. (4) The spatial system of the Macau Peninsula pier district has transformed from a single center to a multi-node, network-linked structure. Its internal spatial differentiation is not only constrained by traditional land use functions but is also driven by complex factors such as tourism economy, residential migration, historical protection, and infrastructure accessibility. (5) Through the analysis of space syntax, it is found that the core integration of the Macau Peninsula pier district is concentrated near Pier 16 and the northern area. The two main roads have good accessibility for motor vehicle travel, and the northern area of the Macau Peninsula pier district has good accessibility for long and short-distance walking. Full article

With its unique environment and strategic value, the near space (NS) has become the focus of global scientific and technological, military, and commercial fields. Aiming at the problem of communication interruption when the aircraft re-enters the atmosphere, to ensure the needs of communication, navigation, and telemetry, tracking, and command (TT&C), this paper proposes an overall integration of communication, navigation, and TT&C (ICNT) signals scheme based on the K/Ka frequency band. Firstly, the K/Ka frequency band is selected according to the ITU frequency division, high-speed communication requirements, advantages of space-based over-the-horizon relay, overcoming the blackout problem, and the development trend of high frequencies. Secondly, the influence of the physical characteristics of the NS on ICNT is analyzed through simulation. The results show that when the K/Ka signal is transmitted in the NS, the path loss changes significantly with the elevation angle. The bottom layer loss at an elevation angle of 90° is between 143.5 and 150.5 dB, and the top layer loss is between 157.5 and 164.4 dB; the maximum attenuation of the bottom layer and the top layer at an elevation angle of 0° is close to 180 dB and 187 dB, respectively. In terms of rainfall attenuation, when a 30 GHz signal passes through a 100 km rain area under moderate rain conditions, the horizontal and vertical polarization losses reach 225 dB and 185 dB, respectively, and the rainfall attenuation increases with the increase in frequency. For gas absorption, the loss of water vapor is higher than that of oxygen molecules; when a 30 GHz signal is transmitted for 100 km, the loss of water vapor is 17 dB, while that of oxygen is 2 dB. The loss of clouds and fog is relatively small, less than 1 dB. Increasing the frequency and the antenna elevation angle can reduce the atmospheric scintillation. In addition, factors such as the plasma sheath and multipath also affect the signal propagation. In terms of modulation technology, the constant envelope signal shows an advantage in spectral efficiency; the new integrated signal obtained by integrating communication, navigation, and TT&C signals into a single K/Ka frequency point has excellent characteristics in the simulation of power spectral density (PSD) and autocorrelation function (ACF), verifying the feasibility of the scheme. The proposed ICNT scheme is expected to provide an innovative solution example for the communication, navigation, and TT&C requirements of NS vehicles during the re-entry phase. Full article

Marine mammal monitoring, a growing field of research, is critical to cetacean conservation. Traditional ‘tagging’ attaches sensors such as GPS to such animals, though these are intrusive and susceptible to infection and, ultimately, death. A less intrusive approach exploits UUV commanded by a human operator above ground. The development of AI for autonomous underwater vehicle navigation models training environments in simulation, providing visual and physical fidelity suitable for sim-to-real transfer. Previous solutions, including UVMS and L2D, provide only satisfactory results, due to poor environment generalisation while sensors including sonar create environmental disturbances. Though rich in features, image data suffer from high dimensionality, providing a state space too great for many machine learning tasks. Underwater environments, susceptible to image noise, further complicate this issue. We propose SWiMM_2.0, coupling a Unity simulation modelling of a BLUEROV UUV with a DRL backend. A pre-processing step exploits a state-of-the-art CMVAE, reducing dimensionality while minimising data loss. Sim-to-real generalisation is validated by prior research. Custom behaviour metrics, unbiased to the naked eye and unprecedented in current ROV simulators, link our objectives ensuring successful ROV behaviour while tracking targets. Our experiments show that SAC maximises the former, achieving near-perfect behaviour while exploiting image data alone. Full article

The cross-domain reentry unmanned flight vehicle passes through thin atmospheres and dense atmospheres when it comes across atmospheres in the near-space area. For the early transition regime, the classical macroscopic and mesoscopic approaches are either not accurate or computational too expensive. The hybrid macro-/mesoscopic method is proposed for simulating rarefied gas flows past a cross-domain reentry spheroid–cone unmanned flight vehicle in the present study. The R26 moment scheme is applied in the main flow from a macroscopic point of view, and the discrete velocity method (DVM) is used for solving the Boltzmann equation from a mesoscopic point of view. The simulation results show that the hybrid macro-/mesoscopic scheme is well-suited for non-equilibrium rarefied gas flows past a cross-domain reentry unmanned flight vehicle. The results obtained in this study are consistent with benchmark results, with a maximum density error of 9%. The maximum errors of the heat transfer coefficient and pressure coefficient are 2% and 4.6%, respectively. In addition, as the Knudsen number (Kn) becomes larger, the thickness of the shock layer at the head of the flight vehicle becomes thicker, and non-equilibrium effects become more critical for the aircraft. Since the Boltzmann–Shakhov equation has only been solved close to the wall of the spacecraft, the computational cost can be considerably saved. Full article

Unmanned Aerial Vehicles (UAVs) are integral to the development of smart city infrastructures, enabling essential services such as real-time surveillance, urban traffic regulation, and cooperative environmental monitoring. UAV-to-UAV communication networks, despite their adaptability, have significant limits stemming from onboard battery constraints, inclement weather, and variable flight trajectories. This work presents a thorough examination of energy and spectral efficiency in UAV-to-UAV communication over four frequency bands: 2.4 GHz, 5.8 GHz, 28 GHz, and 60 GHz. Our MATLAB R2023a simulations include classical free-space path loss, Rayleigh/Rician fading, and real-time mobility profiles, accommodating varied heights (up to 500 m), flight velocities (reaching 15 m/s), and fluctuations in the path loss exponent. Low-frequency bands (e.g., 2.4 GHz) exhibit up to 50% reduced path loss compared to higher mmWave bands for distances exceeding several hundred meters. Energy efficiency (${\eta }_e$) is evaluated by contrasting throughput with total power consumption, indicating that 2.4 GHz initiates at around 0.15 bits/Joule (decreasing to 0.02 bits/Joule after 10 s), whereas 28 GHz and 60 GHz demonstrate markedly worse ${\eta }_e$ (as low as ${10}^{-3}$–${10}^{-4}\mathrm{bits}/\mathrm{Joule}$), resulting from increased path loss and oxygen absorption. Similarly, sub-6 GHz spectral efficiency can attain $4\times {10}^{-12}\mathrm{bps}/\mathrm{Hz}$ in near-line-of-sight scenarios, whereas 60 GHz lines encounter significant attenuation at distances above 200–300 m without sophisticated beamforming techniques. Polynomial-fitting methods indicate that the projected ${\eta }_e$ diverges from actual performance by less than 5% after 10 s of flight, highlighting the feasibility of machine-learning-based techniques for real-time power regulation, beam steering, or multi-band switching. While mmWave UAV communication can provide significant capacity enhancements (100–500 MHz bandwidth), energy efficiency deteriorates markedly without meticulous flight planning or adaptive protocols. We thus advocate using multi-band radios, adaptive modulation, and trajectory optimisation to equilibrate power consumption, ensure connection stability, and meet high data-rate requirements in densely populated, dynamic urban settings. Full article

The number of studies on submarine groundwater discharge (SGD) and the evidence of its significance in biogeochemical cycling and potential impacts on the chemical and ecological status of coastal waters is increasing globally. Here, we briefly present SGD studies from the Baltic Sea identified along the coastlines of Denmark, Finland, Germany, Poland, Sweden and Russia in the southwestern, southern and north–northeastern parts of the Baltic Sea. We introduce a digital SGD map viewer and information platform enabling easy overview and access to information on identified SGD sites in the coastal areas of the Baltic Sea. SGDs potentially transport critical pollutants from urban and agricultural areas on land to the marine environment. The pollutants include nutrients, dissolved organic and inorganic carbon, metals, pharmaceuticals, and other emerging contaminants, potentially harming marine ecosystems and biodiversity and possibly contributing to the poor chemical or ecological status of coastal waters, affecting human and environmental health. We focus on case studies from Finland, Germany, Poland and Denmark that include the results and interpretations from the applied geochemical, geophysical and geological methods, as well as bionic autonomous underwater vehicles (AUVs) for locating, investigating, modelling and visualizing SGD sites in 2D and 3D. The potential Pan-European or even global SGD information platform established within the European Geological Data Infrastructure (EGDI) enables the easy combination and comparison of map layers such as seabed sediment types and coastal habitats. The EGDI map viewer provides easy access to information from SGD studies and may serve as an entry point to relevant information on SGDs, including contents of pollutants, for the scientific community and policy-makers. The information potentially includes the results of model simulations, data from near real-time sensors at permanently installed monitoring stations and surveys in time and space conducted by AUVs. The presented digital SGD information platform is particularly pertinent to the UN Sustainable Development Goal (SDG) No. 14, which focuses on the conservation and sustainable use of oceans and marine resources. Full article

Due to irregular hydrodynamic–aerodynamic coupling, the modeling and simulation of near-surface flight are extremely complex. For the present study, a practical dynamic model and a complete motion simulation method for the solution of such problems were established for engineering applications. A discrete non-linear time-varying dynamics model was employed in order to ensure the universality of the method; thereafter, force models—including gravity, aerodynamic, hydrodynamic, control, and thrust models—were established. It should be noted that a non-linear approach was adopted for the hydrodynamic model, which reflects the influences of waves in real-world situations; in addition, a Proportional–Integral–Derivative (PID) control law was added to realize closed-loop simulation of the motion. Considering a take-off flight as a study case, longitudinal three Degrees of Freedom (DoF) motion was simulated. The velocity, angle of attack, height, and angular velocity were selected as the state vectors in the state–space equations. The results show that, with the equilibrium state as the initial setting for the motion, reasonable time–history curves of the whole take-off phase can be obtained using the proposed approach. Furthermore, it is universally applicable for aircraft operating under hydrodynamic–aerodynamic coupling scenarios, including amphibious aircraft, seaplanes, Wing-in-Ground-Effect (WIGE) aircraft, and Hybrid Aerial–Underwater Vehicles (HAUVs). Full article

Object tracking in thermal video is challenging due to noise, blur, and low contrast. We present TVEMamba, a Mamba-based enhancement framework with near-linear complexity that improves tracking in these conditions. Our approach uses a State Space 2D (SS2D) module integrated with Convolutional Neural Networks (CNNs) to filter, sharpen, and highlight important details. Key components include (i) a denoising module to reduce background noise and enhance image clarity, (ii) an optical flow attention module to handle complex motion and reduce blur, and (iii) entropy-based labeling to create a fully labeled thermal dataset for training and evaluation. TVEMamba outperforms existing methods (DCRGC, RLBHE, IE-CGAN, BBCNN) across multiple datasets (BIRDSAI, FLIR, CAMEL, Autonomous Vehicles, Solar Panels) and achieves higher scores on standard quality metrics (EME, BDIM, DMTE, MDIMTE, LGTA). Extensive tests, including ablation studies and convergence analysis, confirm its robustness. Real-world examples, such as tracking humans, animals, and moving objects for self-driving vehicles and remote sensing, demonstrate the practical value of TVEMamba. Full article

Utilizing fully distributed intelligent control algorithms has enabled the gradual adoption of the multiple unmanned aerial vehicles system for executing Target Tracking and Encirclement missions in industrial and civil applications. Restricted by the evasion behavior of the target, current studies focus on constructing zero-sum game settings, and existing strategy solvers that accommodate continuous state-action spaces have exhibited only modest performance. To tackle the challenges mentioned above, we devise a Stochastic Potential Game framework to model the mission scenario while considering the environment’s limited observability. Furthermore, a multi-agent reinforcement learning method is proposed to estimate the near Nash Equilibrium strategy in the above game scenario, which utilizes time-serial relative kinematic information and obstacle observation. In addition, considering collision avoidance and cooperative tracking, several techniques, such as novel reward functions and recurrent network structures, are presented to optimize the training process. The results of numerical simulations demonstrate that the proposed method exhibits superior search capability for Nash strategies. Moreover, through dynamic virtual experiments conducted with speed and attitude controllers, it has been shown that well-trained actors can effectively act as practical navigators for the real-time swarm control. Full article