To improve small object detection and trajectory estimation from an aerial moving perspective,we propose the Aerial View Attention-PRB(AVA-PRB)model.AVA-PRB integrates two attention mechanisms—Coordinate Attention(CA...To improve small object detection and trajectory estimation from an aerial moving perspective,we propose the Aerial View Attention-PRB(AVA-PRB)model.AVA-PRB integrates two attention mechanisms—Coordinate Attention(CA)and the Convolutional Block Attention Module(CBAM)—to enhance detection accuracy.Additionally,Shape-IoU is employed as the loss function to refine localization precision.Our model further incorporates an adaptive feature fusion mechanism,which optimizes multi-scale object representation,ensuring robust tracking in complex aerial environments.We evaluate the performance of AVA-PRB on two benchmark datasets:Aerial Person Detection and VisDrone2019-Det.The model achieves 60.9%mAP@0.5 on the Aerial Person Detection dataset,and 51.2%mAP@0.5 on VisDrone2019-Det,demonstrating its effectiveness in aerial object detection.Beyond detection,we propose a novel trajectory estimation method that improves movement path prediction under aerial motion.Experimental results indicate that our approach reduces path deviation by up to 64%,effectively mitigating errors caused by rapid camera movements and background variations.By optimizing feature extraction and enhancing spatialtemporal coherence,our method significantly improves object tracking under aerial moving perspectives.This research addresses the limitations of fixed-camera tracking,enhancing flexibility and accuracy in aerial tracking applications.The proposed approach has broad potential for real-world applications,including surveillance,traffic monitoring,and environmental observation.展开更多
Aerial organs in rice,including leaves,stems,and grains,are crucial for photosynthesis,lodging resistance,and yield.Therefore,an in-depth study on the development of these organs can lay a foundation for achieving hig...Aerial organs in rice,including leaves,stems,and grains,are crucial for photosynthesis,lodging resistance,and yield.Therefore,an in-depth study on the development of these organs can lay a foundation for achieving high and stable rice yields.In this study,we isolated a novel slender aerial organ mutant sao,which is characterized by a significant reduction in the width of leaves,stems,and grains.Histological analysis revealed that the slender phenotype of aerial organs in sao is caused by impaired cell proliferation and elongation.展开更多
Low-altitude economy opens up a completely new aerial space for economic growth by enabling brand new services such as fast logistics delivery,timely emergency rescue,and wide-area,high-definition environmental monito...Low-altitude economy opens up a completely new aerial space for economic growth by enabling brand new services such as fast logistics delivery,timely emergency rescue,and wide-area,high-definition environmental monitoring.This new space has many distinct features and therefore faces many new challenges compared with ground-and high-altitude-based information infrastructures.As a result,the rapid and mass development of unmanned aerial vehicles(UAVs)in low-altitude space will inevitably necessitate research on providing ultra-reliable,low-latency,high-capacity.展开更多
With the rapid development of low-altitude economy and unmanned aerial vehicles (UAVs) deployment technology, aerial-ground collaborative delivery (AGCD) is emerging as a novel mode of last-mile delivery, where the ve...With the rapid development of low-altitude economy and unmanned aerial vehicles (UAVs) deployment technology, aerial-ground collaborative delivery (AGCD) is emerging as a novel mode of last-mile delivery, where the vehicle and its onboard UAVs are utilized efficiently. Vehicles not only provide delivery services to customers but also function as mobile ware-houses and launch/recovery platforms for UAVs. This paper addresses the vehicle routing problem with UAVs considering time window and UAV multi-delivery (VRPU-TW&MD). A mixed integer linear programming (MILP) model is developed to mini-mize delivery costs while incorporating constraints related to UAV energy consumption. Subsequently, a micro-evolution aug-mented large neighborhood search (MEALNS) algorithm incor-porating adaptive large neighborhood search (ALNS) and micro-evolution mechanism is proposed. Numerical experiments demonstrate the effectiveness of both the model and algorithm in solving the VRPU-TW&MD. The impact of key parameters on delivery performance is explored by sensitivity analysis.展开更多
Remote sensing plays a pivotal role in environmental monitoring,disaster relief,and urban planning,where accurate scene classification of aerial images is essential.However,conventional convolutional neural networks(C...Remote sensing plays a pivotal role in environmental monitoring,disaster relief,and urban planning,where accurate scene classification of aerial images is essential.However,conventional convolutional neural networks(CNNs)struggle with long-range dependencies and preserving high-resolution features,limiting their effectiveness in complex aerial image analysis.To address these challenges,we propose a Hybrid HRNet-Swin Transformer model that synergizes the strengths of HRNet-W48 for high-resolution segmentation and the Swin Transformer for global feature extraction.This hybrid architecture ensures robust multi-scale feature fusion,capturing fine-grained details and broader contextual relationships in aerial imagery.Our methodology begins with preprocessing steps,including normalization,histogram equalization,and noise reduction,to enhance input data quality.The HRNet-W48 backbone maintains high-resolution feature maps throughout the network,enabling precise segmentation,while the Swin Transformer leverages hierarchical self-attention to model long-range dependencies efficiently.By integrating these components,our model achieves superior performance in segmentation and classification tasks compared to traditional CNNs and standalone transformer models.We evaluate our approach on two benchmark datasets:UC Merced and WHU-RS19.Experimental results demonstrate that the proposed hybrid model outperforms existing methods,achieving state-of-the-art accuracy while maintaining computational efficiency.Specifically,it excels in preserving fine spatial details and contextual understanding,critical for applications like land-use classification and disaster assessment.展开更多
Urban traffic congestion is a significant challenge that contributes to high-density environments in urban areas,adversely impacting the living conditions of urban residents.The concept of urban renewal introduces new...Urban traffic congestion is a significant challenge that contributes to high-density environments in urban areas,adversely impacting the living conditions of urban residents.The concept of urban renewal introduces new requirements and challenges pertaining to urban transportation issues.To mitigate urban traffic congestion,enhance the greening rate of the city,and improve the urban environment,the concept of developing urban aerial ecological corridors is proposed.An analysis of the current state of various urban aerial corridors in different cities indicates that aerial ecological corridors effectively enhance connectivity and accessibility between different spaces,representing a significant strategy for addressing the issue of urban traffic congestion.Aerial ecological corridors have the potential to enhance the vertical space within urban environments,increase the greening rate of cities,and promote the physical and mental health of urban residents.Additionally,these corridors can improve the connectivity of habitat patches and address the developmental needs of biodiversity.Consequently,they serve as a crucial foundation for guiding the future transformation of urban development towards a healthier and greener direction.展开更多
Insect-scale flapping wing aerial robots actuated by piezoelectric materials—known for their high power density and rapid frequency response—have recently garnered increasing attention.However,the limited output dis...Insect-scale flapping wing aerial robots actuated by piezoelectric materials—known for their high power density and rapid frequency response—have recently garnered increasing attention.However,the limited output displacement of piezoelectric actuators results in complex transmission methods that are challenging to assemble.Furthermore,high piezoelectric coefficient materials capable of large displacements for direct wing actuation are fragile,costly,and relatively bulky.This article presents a novel design for minimalist insect-scale aerial robots,where piezoelectric bimorph PZT actuators directly drive two pairs of wings,thus eliminating complex transmission mechanisms and reducing fabrication complexity.These robots demonstrate high liftoff speeds and favorable lift-to-weight ratios,and they can achieve vertical ascent under uncontrolled open-loop conditions.The piezoelectric direct-driven twowing insect-scale aerial robot,based on this approach,features an 8 cm wingspan and a prototype weight of 140 mg,successfully achieving takeoff under unconstrained conditions with an external power source.To further enhance insect-scale aerial robot performance,we optimized the wing-to-actuator ratio and wing arrangement.We propose a biaxial aerial robot with an X-shaped structure,a 2:1 wing-toactuator ratio,a 70 mm wingspan,and a total mass of 160 mg.This structure demonstrates a high lift-to-weight ratio of 2.8:1.During free flight,when powered externally,it attains a maximum takeoff speed exceeding 1 m/s and achieves a vertical takeoff height surpassing 80 cm under uncontrolled conditions.Consequently,it ranks among the fastest prototypes in the milligram-scale weight category.展开更多
The aerial deployment method enables Unmanned Aerial Vehicles(UAVs)to be directly positioned at the required altitude for their mission.This method typically employs folding technology to improve loading efficiency,wi...The aerial deployment method enables Unmanned Aerial Vehicles(UAVs)to be directly positioned at the required altitude for their mission.This method typically employs folding technology to improve loading efficiency,with applications such as the gravity-only aerial deployment of high-aspect-ratio solar-powered UAVs,and aerial takeoff of fixed-wing drones in Mars research.However,the significant morphological changes during deployment are accompanied by strong nonlinear dynamic aerodynamic forces,which result in multiple degrees of freedom and an unstable character.This hinders the description and analysis of unknown dynamic behaviors,further leading to difficulties in the design of deployment strategies and flight control.To address this issue,this paper proposes an analysis method for dynamic behaviors during aerial deployment based on the Variational Autoencoder(VAE).Focusing on the gravity-only deployment problem of highaspect-ratio foldable-wing UAVs,the method encodes the multi-degree-of-freedom unstable motion signals into a low-dimensional feature space through a data-driven approach.By clustering in the feature space,this paper identifies and studies several dynamic behaviors during aerial deployment.The research presented in this paper offers a new method and perspective for feature extraction and analysis of complex and difficult-to-describe extreme flight dynamics,guiding the research on aerial deployment drones design and control strategies.展开更多
The exploration of unmanned aerial vehicle(UAV)swarm systems represents a focal point in the research of multiagent systems,with the investigation of their fission-fusion behavior holding significant theoretical and p...The exploration of unmanned aerial vehicle(UAV)swarm systems represents a focal point in the research of multiagent systems,with the investigation of their fission-fusion behavior holding significant theoretical and practical value.This review systematically examines the methods for fission-fusion of UAV swarms from the perspective of multi-agent systems,encompassing the composition of UAV swarm systems and fission-fusion conditions,information interaction mechanisms,and existing fission-fusion approaches.Firstly,considering the constituent units of UAV swarms and the conditions influencing fission-fusion,this paper categorizes and introduces the UAV swarm systems.It further examines the effects and limitations of fission-fusion methods across various categories and conditions.Secondly,a comprehensive analysis of the prevalent information interaction mechanisms within UAV swarms is conducted from the perspective of information interaction structures.The advantages and limitations of various mechanisms in the context of fission-fusion behaviors are summarized and synthesized.Thirdly,this paper consolidates the existing implementation research findings related to the fission-fusion behavior of UAV swarms,identifies unresolved issues in fission-fusion research,and discusses potential solutions.Finally,the paper concludes with a comprehensive summary and systematically outlines future research opportunities.展开更多
Recovery is a crucial supporting process for carrier aircraft,where a reasonable landing scheduling is expected to guide the fleet landing safely and quickly.Currently,there is little research on this topic,and most o...Recovery is a crucial supporting process for carrier aircraft,where a reasonable landing scheduling is expected to guide the fleet landing safely and quickly.Currently,there is little research on this topic,and most of it neglects potential influence factors,leaving the corresponding supporting efficiency questionable.In this paper,we study the landing scheduling problem for carrier aircraft considering the effects of bolting and aerial refueling.Based on the analysis of recovery mode involving the above factors,two types of primary constraints(i.e.,fuel constraint and wake interval constraint)are first described.Then,taking the landing sequencing as decision variables,a combinatorial optimization model with a compound objective function is formulated.Aiming at an efficient solution,an improved firefly algorithm is designed by integrating multiple evolutionary operators.In addition,a dynamic replanning mechanism is introduced to deal with special situations(i.e.,the occurrence of bolting and fuel shortage),where the high efficiency of the designed algorithm facilitates the online scheduling adjustment within seconds.Finally,numerical simulations with sufficient and insufficient fuel cases are both carried out,highlighting the necessity to consider bolting and aerial refueling during the planning procedure.Simulation results reveal that a higher bolting probability,as well as extra aerial refueling operations caused by fuel shortage,will lead to longer recovery complete time.Meanwhile,due to the strong optimum-seeking capability and solution efficiency of the improved algorithm,adaptive scheduling can be generated within milliseconds to deal with special situations,significantly improving the safety and efficiency of the recovery process.An animation is accessible at bilibili.com/video/BV1QprKY2EwD.展开更多
Real-time and accurate drogue pose measurement during docking is basic and critical for Autonomous Aerial Refueling(AAR).Vision measurement is the best practicable technique,but its measurement accuracy and robustness...Real-time and accurate drogue pose measurement during docking is basic and critical for Autonomous Aerial Refueling(AAR).Vision measurement is the best practicable technique,but its measurement accuracy and robustness are easily affected by limited computing power of airborne equipment,complex aerial scenes and partial occlusion.To address the above challenges,we propose a novel drogue keypoint detection and pose measurement algorithm based on monocular vision,and realize real-time processing on airborne embedded devices.Firstly,a lightweight network is designed with structural re-parameterization to reduce computational cost and improve inference speed.And a sub-pixel level keypoints prediction head and loss functions are adopted to improve keypoint detection accuracy.Secondly,a closed-form solution of drogue pose is computed based on double spatial circles,followed by a nonlinear refinement based on Levenberg-Marquardt optimization.Both virtual simulation and physical simulation experiments have been used to test the proposed method.In the virtual simulation,the mean pixel error of the proposed method is 0.787 pixels,which is significantly superior to that of other methods.In the physical simulation,the mean relative measurement error is 0.788%,and the mean processing time is 13.65 ms on embedded devices.展开更多
Modeling the dynamics of flapping wing aerial vehicle is challenging due to the complexity of aerodynamic effects and mechanical structures.The aim of this work is to develop an accurate dynamics model of flapping win...Modeling the dynamics of flapping wing aerial vehicle is challenging due to the complexity of aerodynamic effects and mechanical structures.The aim of this work is to develop an accurate dynamics model of flapping wing aerial vehicle based on real flight data.We propose a modeling framework that combines rigid body dynamics with a neural network to predict aerodynamic effects.By incorporating the concept of flapping phase,we significantly enhance the network’s ability to analyze transient aerodynamic behavior.We design and utilize a phase-functioned neural network structure for aerodynamic predictions and train the network using real flight data.Evaluation results show that the network can predict aerodynamic effects and demonstrate clear physical significance.We verify that the framework can be used for dynamic propagation and is expected to be utilized for building simulators for flapping wing aerial vehicles.展开更多
This paper proposes a novel blended hyper-cellular architecture for low-altitude aerial intelligent networks(LAINs)to provide agile coverage tailored to active air routes and takeoff/landing spots.Traditional cellular...This paper proposes a novel blended hyper-cellular architecture for low-altitude aerial intelligent networks(LAINs)to provide agile coverage tailored to active air routes and takeoff/landing spots.Traditional cellular networks struggle to meet the dynamic demands of low-altitude UAV communications due to their rigid structures.The hyper-cellular network(HCN)architecture separates control and traffic coverage,enabling flexible and energy-efficient operations.The key components include control base stations(CBSs)for wide-area signaling coverage and traffic base stations(TBSs)that can be dynamically activated based on traffic demands.The proposed solution also integrates space information networks(SINs)to enhance the coverage efficiency.Key technologies such as all-G CBS using RISC-V architecture,AI-powered radio maps for low-altitude environments,and agile TBS coverage adaptation are introduced with some preliminary studies.These designs aim to address challenges like mobility management,interference coordination,and the need for real-time spectrum sharing in blended satellite-terrestrial networks.The proposed solution offers a scalable and agile framework to support the rapidly growing demand for reliable,low-latency,and high-capacity UAV communications in urban environments.展开更多
This paper investigates the power generation characteristics of solar cells mounted on unmanned aerial vehicles(UAVs)under the coupled influence of flight conditions and the sur-rounding environment.Firstly,the study ...This paper investigates the power generation characteristics of solar cells mounted on unmanned aerial vehicles(UAVs)under the coupled influence of flight conditions and the sur-rounding environment.Firstly,the study reveals that the voltage,current,and power output of the solar cells undergo consistent temporal variations throughout the day,primarily driven by voltage fluctuations,with a peak occurring around noon.Secondly,it is observed that the cells’performance is significantly more influenced by temporal variations in external light intensity than by temperature changes resulting from variations in flight speed.Finally,the study finds that the impact of flight altitude on the cells’performance is slightly more pronounced than the influence of temporal variations in external light intensity.展开更多
Accurate,reliable,and regularly updated information is necessary for targeted management of forest stands.This information is usually obtained from sample-based field inventory data.Due to the time-consuming and costl...Accurate,reliable,and regularly updated information is necessary for targeted management of forest stands.This information is usually obtained from sample-based field inventory data.Due to the time-consuming and costly procedure of forest inventory,it is imperative to generate and use the resulting data optimally.Integrating field inventory information with remote sensing data increases the value of field approaches,such as national forest inventories.This study investigated the optimal integration of forest inventory data with aerial image-based canopy height models(CHM)for forest growing stock estimation.For this purpose,fixed-area and angle-count plots from a forest area in Austria were used to assess which type of inventory system is more suitable when the field data is integrated with aerial image analysis.Although a higher correlation was observed between remotely predicted growing stocks and field inventory values for fixed-area plots,the paired t-test results revealed no statistical difference between the two methods.The R2 increased by 0.08 points and the RMSE decreased by 7.7 percentage points(24.8m^(3)·ha^(−1))using fixed-area plots.Since tree height is the most critical variable essential for modeling forest growing stock using aerial images,we also compared the tree heights obtained from CHM to those from the typical field inventory approach.The result shows a high correlation(R^(2)=0.781)between the tree heights extracted from the CHM and those measured in the field.However,the correlation decreased by 0.113 points and the RMSE increased by 4.2 percentage points(1.04m)when the allometrically derived tree heights were analyzed.Moreover,the results of the paired t-test revealed that there is no significant statistical difference between the tree heights extracted from CHM and those measured in the field,but there is a significant statistical difference when the CHM-derived and the allometrically-derived heights were compared.This proved that image-based CHM can obtain more accurate tree height information than field inventory estimations.Overall,the results of this study demonstrated that image-based CHM can be integrated into the forest inventory data at large scales and provide reliable information on forest growing stock.The produced maps reflect the variability of growth conditions and developmental stages of different forest stands.This information is required to characterize the status and changes,e.g.,in forest structure diversity,parameters for volume,and can be used for forest aboveground biomass estimation,which plays an important role in managing and controlling forest resources in mid-term forest management.This is of particular interest to forest managers and forest ecologists.展开更多
Unmanned aerial vehicles(UAVs)have become crucial tools in moving target tracking due to their agility and ability to operate in complex,dynamic environments.UAVs must meet several requirements to achieve stable track...Unmanned aerial vehicles(UAVs)have become crucial tools in moving target tracking due to their agility and ability to operate in complex,dynamic environments.UAVs must meet several requirements to achieve stable tracking,including maintaining continuous target visibility amidst occlusions,ensuring flight safety,and achieving smooth trajectory planning.This paper reviews the latest advancements in UAV-based target tracking,highlighting information prediction,tracking strategies,and swarm cooperation.To address challenges including target visibility and occlusion,real-time prediction and tracking in dynamic environments,flight safety and coordination,resource management and energy efficiency,the paper identifies future research directions aimed at improving the performance,reliability,and scalability of UAV tracking system.展开更多
The large-scale development of the lowaltitude economy imposes increasingly stringent requirements on the supporting information infrastructure,necessitating the establishment of a low-altitude intelligent network(LAI...The large-scale development of the lowaltitude economy imposes increasingly stringent requirements on the supporting information infrastructure,necessitating the establishment of a low-altitude intelligent network(LAIN)with wide-area communication,high-precision navigation,and efficient supervision capabilities.Benefiting from its broad coverage,high reliability,and large bandwidth,the 5G cellular network serves as a critical foundation for LAIN construction.However,conventional cellular networks are primarily designed for two-dimensional terrestrial scenarios,and thus face significant limitations in coverage and interference resistance within complex three-dimensional low-altitude environments.To address the unique demands of LAIN applications,key challenges must be tackled,including achieving seamless three-dimensional coverage,mitigating interference in multi-dimensional network deployments,and ensuring stringent requirements for service quality and security supervision.This paper proposes an integrated LAIN architecture characterized by the convergence of communication,navigation,sensing,and management,enhanced with artificial intelligence and security mechanisms to improve overall system intelligence and resilience.Furthermore,this paper conducts an in-depth analysis of the critical challenges in LAIN deployment,explores enabling technologies to address these issues,and offers insights into the future development direction of low-altitude intelligent networks.展开更多
This article investigates the approaching control for fixed-wing Unmanned Aerial Vehi-cle(UAV)aerial recovery in the presence of pre-specified performance requirements,complex air-flows,maneuvering flight of transport...This article investigates the approaching control for fixed-wing Unmanned Aerial Vehi-cle(UAV)aerial recovery in the presence of pre-specified performance requirements,complex air-flows,maneuvering flight of transport aircraft,and different initial deviations.First,a novelcontrol-oriented Six-Degree-Of-Freedom(6-DOF)UAV model considering airflow disturbancesis established for better consistency with the actual UAV system.Then,to achieve satisfactory per-formance in the approaching process,a Flexible Appointed-time Prescribed Performance Control(FAPPC)algorithm,with the features of user-specified time convergence,no overshoot,indepen-dence from the initial value,and singularity-free,is proposed.Specifically,to solve the singularityissue encountered by the existing PPC methods in dealing with sudden disturbances,an adaptiveadjustment signal is introduced in FAPPC to perceive the threat of increasing error and relax thepreset boundaries appropriately.Moreover,minimum learning parameter-based neural networkestimators are developed to approximate unknown lumped disturbances at a low computationalcost.Finally,the stability of the closed system is analyzed via Lyapunov synthesis,and the effective-ness and advantages of the proposed control scheme are demonstrated via simulation andHardware-In-the-Loop(HIL)experimental validation.展开更多
Recent studies have shown that mucilage secretion from aerial roots is an essential feature of modern maize inbred lines,with some retaining the nitrogen-fixing capabilities of ancient landraces.To explore the genetic...Recent studies have shown that mucilage secretion from aerial roots is an essential feature of modern maize inbred lines,with some retaining the nitrogen-fixing capabilities of ancient landraces.To explore the genetic basis of nitrogen fixation in mucilage and its evolution from teosinte(Zea mays ssp.mexicana)to modern maize,we developed a recombinant inbred line(RIL)population from teosinte and cultivated it under low-nitrogen conditions.Large-scale,multi-year,and multi-environment analyses of RIL-Teo,Doubled Haploid-A(DH-A),Doubled Haploid-B(DH-B),and association populations led to the identification of 15 quantitative trait loci(QTL),68 quantitative trait nucleotides(QTN),and 59 candidate genes linked to mucilage secretion from aerial roots.Functional verification of the candidate gene ZmAco3,which is associated with mucilage secretion in aerial roots,demonstrated that deletion of this gene resulted in a reduction in mucilage secretion in aerial roots.In addition,most maize inbred lines exhibited stronger mucilage secretion from aerial roots under low-nitrogen conditions than under normal-nitrogen conditions.We categorized mucilage secretion into constitutive and low-nitrogen-inducible types.Through genotype-by-environment interaction studies,8 QTL,16 QTN,and 19 candidate genes were identified,revealing the genetic mechanisms underlying mucilage secretion under low-nitrogen conditions.These findings provide a comprehensive genetic analysis of the mucilage-secreting ability of maize aerial roots,contributing to our understanding of nitrogen fixation and offering potential avenues for enhancing nitrogen fixation in modern maize lines.This research advances knowledge of plant nutrient acquisition strategies and has implications for sustainable agricultural practices.展开更多
This study compared the control effect of 110 g/L etoxazole SC,15%abamectin·etoxazole SC,30%cyetpyrafen SC,43%bifenazate SC and 1.8%abamectin EC five acaricides sprayed by unmanned aerial vehicle(UAV)on Panonychu...This study compared the control effect of 110 g/L etoxazole SC,15%abamectin·etoxazole SC,30%cyetpyrafen SC,43%bifenazate SC and 1.8%abamectin EC five acaricides sprayed by unmanned aerial vehicle(UAV)on Panonychus citri,aiming to screen out the appropriate acaricide for the control of this pest by UAV spraying.The results showed that 15%abamectin·etoxazole SC and 30%cyetpyrafen SC had the highest control efficacy,which remained above 90%14 d after application.Secondary performance was observed in 43%bifenazate SC and 110 g/L etoxazole SC,which demonstrated enhancing control effect.However,1.8%abamectin EC showed slower effect.Considering the control effect and population reduction rate of P.citri,15%abamectin·etoxazole SC and 30%cyetpyrafen SC were suggested as the effective acaricides for the control of this pest.展开更多
基金funded by theNational Science and TechnologyCouncil(NSTC),Taiwan,under grant numbers NSTC 113-2634-F-A49-007 and NSTC 112-2634-F-A49-007.
文摘To improve small object detection and trajectory estimation from an aerial moving perspective,we propose the Aerial View Attention-PRB(AVA-PRB)model.AVA-PRB integrates two attention mechanisms—Coordinate Attention(CA)and the Convolutional Block Attention Module(CBAM)—to enhance detection accuracy.Additionally,Shape-IoU is employed as the loss function to refine localization precision.Our model further incorporates an adaptive feature fusion mechanism,which optimizes multi-scale object representation,ensuring robust tracking in complex aerial environments.We evaluate the performance of AVA-PRB on two benchmark datasets:Aerial Person Detection and VisDrone2019-Det.The model achieves 60.9%mAP@0.5 on the Aerial Person Detection dataset,and 51.2%mAP@0.5 on VisDrone2019-Det,demonstrating its effectiveness in aerial object detection.Beyond detection,we propose a novel trajectory estimation method that improves movement path prediction under aerial motion.Experimental results indicate that our approach reduces path deviation by up to 64%,effectively mitigating errors caused by rapid camera movements and background variations.By optimizing feature extraction and enhancing spatialtemporal coherence,our method significantly improves object tracking under aerial moving perspectives.This research addresses the limitations of fixed-camera tracking,enhancing flexibility and accuracy in aerial tracking applications.The proposed approach has broad potential for real-world applications,including surveillance,traffic monitoring,and environmental observation.
基金supported by the Sichuan Science and Technology Program,China(Grant No.2024JDRC0064)the Chongqing Talent Program Foundation,China(Grant No.cstc2024ycjh-bgzxm0063)+1 种基金the National Natural Science Foundation of China(Grant No.32470354)the Sichuan Science and Technology Innovation and Entrepreneurship Seedling Foundation,China(Grant No.2024JDRC0064).
文摘Aerial organs in rice,including leaves,stems,and grains,are crucial for photosynthesis,lodging resistance,and yield.Therefore,an in-depth study on the development of these organs can lay a foundation for achieving high and stable rice yields.In this study,we isolated a novel slender aerial organ mutant sao,which is characterized by a significant reduction in the width of leaves,stems,and grains.Histological analysis revealed that the slender phenotype of aerial organs in sao is caused by impaired cell proliferation and elongation.
文摘Low-altitude economy opens up a completely new aerial space for economic growth by enabling brand new services such as fast logistics delivery,timely emergency rescue,and wide-area,high-definition environmental monitoring.This new space has many distinct features and therefore faces many new challenges compared with ground-and high-altitude-based information infrastructures.As a result,the rapid and mass development of unmanned aerial vehicles(UAVs)in low-altitude space will inevitably necessitate research on providing ultra-reliable,low-latency,high-capacity.
基金supported by the Fundamental Research Funds for the Central Universities(2024JBZX038)the National Natural Science Foundation of China(62076023).
文摘With the rapid development of low-altitude economy and unmanned aerial vehicles (UAVs) deployment technology, aerial-ground collaborative delivery (AGCD) is emerging as a novel mode of last-mile delivery, where the vehicle and its onboard UAVs are utilized efficiently. Vehicles not only provide delivery services to customers but also function as mobile ware-houses and launch/recovery platforms for UAVs. This paper addresses the vehicle routing problem with UAVs considering time window and UAV multi-delivery (VRPU-TW&MD). A mixed integer linear programming (MILP) model is developed to mini-mize delivery costs while incorporating constraints related to UAV energy consumption. Subsequently, a micro-evolution aug-mented large neighborhood search (MEALNS) algorithm incor-porating adaptive large neighborhood search (ALNS) and micro-evolution mechanism is proposed. Numerical experiments demonstrate the effectiveness of both the model and algorithm in solving the VRPU-TW&MD. The impact of key parameters on delivery performance is explored by sensitivity analysis.
基金supported by the ITP(Institute of Information&Communications Technology Planning&Evaluation)-ICAN(ICT Challenge and Advanced Network of HRD)(ITP-2025-RS-2022-00156326,33)grant funded by the Korea government(Ministry of Science and ICT)the Deanship of Research and Graduate Studies at King Khalid University for funding this work through the Large Group Project under grant number(RGP2/568/45)the Deanship of Scientific Research at Northern Border University,Arar,Saudi Arabia,for funding this research work through the Project Number"NBU-FFR-2025-231-03".
文摘Remote sensing plays a pivotal role in environmental monitoring,disaster relief,and urban planning,where accurate scene classification of aerial images is essential.However,conventional convolutional neural networks(CNNs)struggle with long-range dependencies and preserving high-resolution features,limiting their effectiveness in complex aerial image analysis.To address these challenges,we propose a Hybrid HRNet-Swin Transformer model that synergizes the strengths of HRNet-W48 for high-resolution segmentation and the Swin Transformer for global feature extraction.This hybrid architecture ensures robust multi-scale feature fusion,capturing fine-grained details and broader contextual relationships in aerial imagery.Our methodology begins with preprocessing steps,including normalization,histogram equalization,and noise reduction,to enhance input data quality.The HRNet-W48 backbone maintains high-resolution feature maps throughout the network,enabling precise segmentation,while the Swin Transformer leverages hierarchical self-attention to model long-range dependencies efficiently.By integrating these components,our model achieves superior performance in segmentation and classification tasks compared to traditional CNNs and standalone transformer models.We evaluate our approach on two benchmark datasets:UC Merced and WHU-RS19.Experimental results demonstrate that the proposed hybrid model outperforms existing methods,achieving state-of-the-art accuracy while maintaining computational efficiency.Specifically,it excels in preserving fine spatial details and contextual understanding,critical for applications like land-use classification and disaster assessment.
基金Sponsored by Research Team Project of Anhui Xinhua University(kytd202202)Anhui Provincial Undergraduate Innovation Training Program(S202212216146,S202212216133,S202212216138,AH202112216114)Key Project of Anhui Provincial Higher Education Scientific Research Project(Natural Science)(2022AH051861,2024AH050601).
文摘Urban traffic congestion is a significant challenge that contributes to high-density environments in urban areas,adversely impacting the living conditions of urban residents.The concept of urban renewal introduces new requirements and challenges pertaining to urban transportation issues.To mitigate urban traffic congestion,enhance the greening rate of the city,and improve the urban environment,the concept of developing urban aerial ecological corridors is proposed.An analysis of the current state of various urban aerial corridors in different cities indicates that aerial ecological corridors effectively enhance connectivity and accessibility between different spaces,representing a significant strategy for addressing the issue of urban traffic congestion.Aerial ecological corridors have the potential to enhance the vertical space within urban environments,increase the greening rate of cities,and promote the physical and mental health of urban residents.Additionally,these corridors can improve the connectivity of habitat patches and address the developmental needs of biodiversity.Consequently,they serve as a crucial foundation for guiding the future transformation of urban development towards a healthier and greener direction.
基金supported by the National Natural Science Foundation of China(No.52475039)。
文摘Insect-scale flapping wing aerial robots actuated by piezoelectric materials—known for their high power density and rapid frequency response—have recently garnered increasing attention.However,the limited output displacement of piezoelectric actuators results in complex transmission methods that are challenging to assemble.Furthermore,high piezoelectric coefficient materials capable of large displacements for direct wing actuation are fragile,costly,and relatively bulky.This article presents a novel design for minimalist insect-scale aerial robots,where piezoelectric bimorph PZT actuators directly drive two pairs of wings,thus eliminating complex transmission mechanisms and reducing fabrication complexity.These robots demonstrate high liftoff speeds and favorable lift-to-weight ratios,and they can achieve vertical ascent under uncontrolled open-loop conditions.The piezoelectric direct-driven twowing insect-scale aerial robot,based on this approach,features an 8 cm wingspan and a prototype weight of 140 mg,successfully achieving takeoff under unconstrained conditions with an external power source.To further enhance insect-scale aerial robot performance,we optimized the wing-to-actuator ratio and wing arrangement.We propose a biaxial aerial robot with an X-shaped structure,a 2:1 wing-toactuator ratio,a 70 mm wingspan,and a total mass of 160 mg.This structure demonstrates a high lift-to-weight ratio of 2.8:1.During free flight,when powered externally,it attains a maximum takeoff speed exceeding 1 m/s and achieves a vertical takeoff height surpassing 80 cm under uncontrolled conditions.Consequently,it ranks among the fastest prototypes in the milligram-scale weight category.
基金co-supported by the Natural Science Basic Research Program of Shaanxi,China(No.2023-JC-QN-0043)the ND Basic Research Funds,China(No.G2022WD).
文摘The aerial deployment method enables Unmanned Aerial Vehicles(UAVs)to be directly positioned at the required altitude for their mission.This method typically employs folding technology to improve loading efficiency,with applications such as the gravity-only aerial deployment of high-aspect-ratio solar-powered UAVs,and aerial takeoff of fixed-wing drones in Mars research.However,the significant morphological changes during deployment are accompanied by strong nonlinear dynamic aerodynamic forces,which result in multiple degrees of freedom and an unstable character.This hinders the description and analysis of unknown dynamic behaviors,further leading to difficulties in the design of deployment strategies and flight control.To address this issue,this paper proposes an analysis method for dynamic behaviors during aerial deployment based on the Variational Autoencoder(VAE).Focusing on the gravity-only deployment problem of highaspect-ratio foldable-wing UAVs,the method encodes the multi-degree-of-freedom unstable motion signals into a low-dimensional feature space through a data-driven approach.By clustering in the feature space,this paper identifies and studies several dynamic behaviors during aerial deployment.The research presented in this paper offers a new method and perspective for feature extraction and analysis of complex and difficult-to-describe extreme flight dynamics,guiding the research on aerial deployment drones design and control strategies.
基金supported by the National Natural Science Foundation of China(U20B2042).
文摘The exploration of unmanned aerial vehicle(UAV)swarm systems represents a focal point in the research of multiagent systems,with the investigation of their fission-fusion behavior holding significant theoretical and practical value.This review systematically examines the methods for fission-fusion of UAV swarms from the perspective of multi-agent systems,encompassing the composition of UAV swarm systems and fission-fusion conditions,information interaction mechanisms,and existing fission-fusion approaches.Firstly,considering the constituent units of UAV swarms and the conditions influencing fission-fusion,this paper categorizes and introduces the UAV swarm systems.It further examines the effects and limitations of fission-fusion methods across various categories and conditions.Secondly,a comprehensive analysis of the prevalent information interaction mechanisms within UAV swarms is conducted from the perspective of information interaction structures.The advantages and limitations of various mechanisms in the context of fission-fusion behaviors are summarized and synthesized.Thirdly,this paper consolidates the existing implementation research findings related to the fission-fusion behavior of UAV swarms,identifies unresolved issues in fission-fusion research,and discusses potential solutions.Finally,the paper concludes with a comprehensive summary and systematically outlines future research opportunities.
基金the financial support of the National Natural Science Foundation of China(12102077,12161076)the Natural Science and Technology Program of Liaoning Province(2023-BS-061).
文摘Recovery is a crucial supporting process for carrier aircraft,where a reasonable landing scheduling is expected to guide the fleet landing safely and quickly.Currently,there is little research on this topic,and most of it neglects potential influence factors,leaving the corresponding supporting efficiency questionable.In this paper,we study the landing scheduling problem for carrier aircraft considering the effects of bolting and aerial refueling.Based on the analysis of recovery mode involving the above factors,two types of primary constraints(i.e.,fuel constraint and wake interval constraint)are first described.Then,taking the landing sequencing as decision variables,a combinatorial optimization model with a compound objective function is formulated.Aiming at an efficient solution,an improved firefly algorithm is designed by integrating multiple evolutionary operators.In addition,a dynamic replanning mechanism is introduced to deal with special situations(i.e.,the occurrence of bolting and fuel shortage),where the high efficiency of the designed algorithm facilitates the online scheduling adjustment within seconds.Finally,numerical simulations with sufficient and insufficient fuel cases are both carried out,highlighting the necessity to consider bolting and aerial refueling during the planning procedure.Simulation results reveal that a higher bolting probability,as well as extra aerial refueling operations caused by fuel shortage,will lead to longer recovery complete time.Meanwhile,due to the strong optimum-seeking capability and solution efficiency of the improved algorithm,adaptive scheduling can be generated within milliseconds to deal with special situations,significantly improving the safety and efficiency of the recovery process.An animation is accessible at bilibili.com/video/BV1QprKY2EwD.
基金supported by the National Science Fund for Distinguished Young Scholars,China(No.51625501)Aeronautical Science Foundation of China(No.20240046051002)National Natural Science Foundation of China(No.52005028).
文摘Real-time and accurate drogue pose measurement during docking is basic and critical for Autonomous Aerial Refueling(AAR).Vision measurement is the best practicable technique,but its measurement accuracy and robustness are easily affected by limited computing power of airborne equipment,complex aerial scenes and partial occlusion.To address the above challenges,we propose a novel drogue keypoint detection and pose measurement algorithm based on monocular vision,and realize real-time processing on airborne embedded devices.Firstly,a lightweight network is designed with structural re-parameterization to reduce computational cost and improve inference speed.And a sub-pixel level keypoints prediction head and loss functions are adopted to improve keypoint detection accuracy.Secondly,a closed-form solution of drogue pose is computed based on double spatial circles,followed by a nonlinear refinement based on Levenberg-Marquardt optimization.Both virtual simulation and physical simulation experiments have been used to test the proposed method.In the virtual simulation,the mean pixel error of the proposed method is 0.787 pixels,which is significantly superior to that of other methods.In the physical simulation,the mean relative measurement error is 0.788%,and the mean processing time is 13.65 ms on embedded devices.
基金supported by National Natural Science Foundation of China under Grant No.62236007the specialized research projects of Huanjiang Laboratory.
文摘Modeling the dynamics of flapping wing aerial vehicle is challenging due to the complexity of aerodynamic effects and mechanical structures.The aim of this work is to develop an accurate dynamics model of flapping wing aerial vehicle based on real flight data.We propose a modeling framework that combines rigid body dynamics with a neural network to predict aerodynamic effects.By incorporating the concept of flapping phase,we significantly enhance the network’s ability to analyze transient aerodynamic behavior.We design and utilize a phase-functioned neural network structure for aerodynamic predictions and train the network using real flight data.Evaluation results show that the network can predict aerodynamic effects and demonstrate clear physical significance.We verify that the framework can be used for dynamic propagation and is expected to be utilized for building simulators for flapping wing aerial vehicles.
基金Feng Wei was supported by the National Natural Science Foundation of China under Grant 62425110.
文摘This paper proposes a novel blended hyper-cellular architecture for low-altitude aerial intelligent networks(LAINs)to provide agile coverage tailored to active air routes and takeoff/landing spots.Traditional cellular networks struggle to meet the dynamic demands of low-altitude UAV communications due to their rigid structures.The hyper-cellular network(HCN)architecture separates control and traffic coverage,enabling flexible and energy-efficient operations.The key components include control base stations(CBSs)for wide-area signaling coverage and traffic base stations(TBSs)that can be dynamically activated based on traffic demands.The proposed solution also integrates space information networks(SINs)to enhance the coverage efficiency.Key technologies such as all-G CBS using RISC-V architecture,AI-powered radio maps for low-altitude environments,and agile TBS coverage adaptation are introduced with some preliminary studies.These designs aim to address challenges like mobility management,interference coordination,and the need for real-time spectrum sharing in blended satellite-terrestrial networks.The proposed solution offers a scalable and agile framework to support the rapidly growing demand for reliable,low-latency,and high-capacity UAV communications in urban environments.
基金supported by the National Natural Science Foundation of China(Nos.12464010,52462035)2022 Jiangxi Province High-Level and High-Skilled Leading Talent Training Project Selected(No.63)+1 种基金Jiujiang“Xuncheng Talents”(No.JJXC2023032)Jiujiang Basic Research Program Project(2025).
文摘This paper investigates the power generation characteristics of solar cells mounted on unmanned aerial vehicles(UAVs)under the coupled influence of flight conditions and the sur-rounding environment.Firstly,the study reveals that the voltage,current,and power output of the solar cells undergo consistent temporal variations throughout the day,primarily driven by voltage fluctuations,with a peak occurring around noon.Secondly,it is observed that the cells’performance is significantly more influenced by temporal variations in external light intensity than by temperature changes resulting from variations in flight speed.Finally,the study finds that the impact of flight altitude on the cells’performance is slightly more pronounced than the influence of temporal variations in external light intensity.
基金supported by grants provided within the research project»EO4Forest:Use of multi-temporal Sentinel-2 and VHR Pleiades stereo data for sustainable forest monitoring and management«funded by the Austrian Federal Ministry for Climate Action,Environ-ment,Energy,Mobility,Innovation and Technology(BMK)within the FFG Austrian Space Applications Program ASAP 12(grant agreement number 854027).
文摘Accurate,reliable,and regularly updated information is necessary for targeted management of forest stands.This information is usually obtained from sample-based field inventory data.Due to the time-consuming and costly procedure of forest inventory,it is imperative to generate and use the resulting data optimally.Integrating field inventory information with remote sensing data increases the value of field approaches,such as national forest inventories.This study investigated the optimal integration of forest inventory data with aerial image-based canopy height models(CHM)for forest growing stock estimation.For this purpose,fixed-area and angle-count plots from a forest area in Austria were used to assess which type of inventory system is more suitable when the field data is integrated with aerial image analysis.Although a higher correlation was observed between remotely predicted growing stocks and field inventory values for fixed-area plots,the paired t-test results revealed no statistical difference between the two methods.The R2 increased by 0.08 points and the RMSE decreased by 7.7 percentage points(24.8m^(3)·ha^(−1))using fixed-area plots.Since tree height is the most critical variable essential for modeling forest growing stock using aerial images,we also compared the tree heights obtained from CHM to those from the typical field inventory approach.The result shows a high correlation(R^(2)=0.781)between the tree heights extracted from the CHM and those measured in the field.However,the correlation decreased by 0.113 points and the RMSE increased by 4.2 percentage points(1.04m)when the allometrically derived tree heights were analyzed.Moreover,the results of the paired t-test revealed that there is no significant statistical difference between the tree heights extracted from CHM and those measured in the field,but there is a significant statistical difference when the CHM-derived and the allometrically-derived heights were compared.This proved that image-based CHM can obtain more accurate tree height information than field inventory estimations.Overall,the results of this study demonstrated that image-based CHM can be integrated into the forest inventory data at large scales and provide reliable information on forest growing stock.The produced maps reflect the variability of growth conditions and developmental stages of different forest stands.This information is required to characterize the status and changes,e.g.,in forest structure diversity,parameters for volume,and can be used for forest aboveground biomass estimation,which plays an important role in managing and controlling forest resources in mid-term forest management.This is of particular interest to forest managers and forest ecologists.
基金financial support provided by the Natural Science Foundation of Hunan Province of China(Grant No.2021JJ10045)the Open Research Subject of State Key Laboratory of Intelligent Game(Grant No.ZBKF-24-01)+1 种基金the Postdoctoral Fellowship Program of CPSF(Grant No.GZB20240989)the China Postdoctoral Science Foundation(Grant No.2024M754304)。
文摘Unmanned aerial vehicles(UAVs)have become crucial tools in moving target tracking due to their agility and ability to operate in complex,dynamic environments.UAVs must meet several requirements to achieve stable tracking,including maintaining continuous target visibility amidst occlusions,ensuring flight safety,and achieving smooth trajectory planning.This paper reviews the latest advancements in UAV-based target tracking,highlighting information prediction,tracking strategies,and swarm cooperation.To address challenges including target visibility and occlusion,real-time prediction and tracking in dynamic environments,flight safety and coordination,resource management and energy efficiency,the paper identifies future research directions aimed at improving the performance,reliability,and scalability of UAV tracking system.
文摘The large-scale development of the lowaltitude economy imposes increasingly stringent requirements on the supporting information infrastructure,necessitating the establishment of a low-altitude intelligent network(LAIN)with wide-area communication,high-precision navigation,and efficient supervision capabilities.Benefiting from its broad coverage,high reliability,and large bandwidth,the 5G cellular network serves as a critical foundation for LAIN construction.However,conventional cellular networks are primarily designed for two-dimensional terrestrial scenarios,and thus face significant limitations in coverage and interference resistance within complex three-dimensional low-altitude environments.To address the unique demands of LAIN applications,key challenges must be tackled,including achieving seamless three-dimensional coverage,mitigating interference in multi-dimensional network deployments,and ensuring stringent requirements for service quality and security supervision.This paper proposes an integrated LAIN architecture characterized by the convergence of communication,navigation,sensing,and management,enhanced with artificial intelligence and security mechanisms to improve overall system intelligence and resilience.Furthermore,this paper conducts an in-depth analysis of the critical challenges in LAIN deployment,explores enabling technologies to address these issues,and offers insights into the future development direction of low-altitude intelligent networks.
基金funded by the National Natural Science Foundation of China(Nos.62173022,61673042)the Academic Excellence Foundation of Beihang University for Ph.D.Studentsthe Outstanding Research Project of Shen Yuan Honors College,Beihang University,China(No.230123104)。
文摘This article investigates the approaching control for fixed-wing Unmanned Aerial Vehi-cle(UAV)aerial recovery in the presence of pre-specified performance requirements,complex air-flows,maneuvering flight of transport aircraft,and different initial deviations.First,a novelcontrol-oriented Six-Degree-Of-Freedom(6-DOF)UAV model considering airflow disturbancesis established for better consistency with the actual UAV system.Then,to achieve satisfactory per-formance in the approaching process,a Flexible Appointed-time Prescribed Performance Control(FAPPC)algorithm,with the features of user-specified time convergence,no overshoot,indepen-dence from the initial value,and singularity-free,is proposed.Specifically,to solve the singularityissue encountered by the existing PPC methods in dealing with sudden disturbances,an adaptiveadjustment signal is introduced in FAPPC to perceive the threat of increasing error and relax thepreset boundaries appropriately.Moreover,minimum learning parameter-based neural networkestimators are developed to approximate unknown lumped disturbances at a low computationalcost.Finally,the stability of the closed system is analyzed via Lyapunov synthesis,and the effective-ness and advantages of the proposed control scheme are demonstrated via simulation andHardware-In-the-Loop(HIL)experimental validation.
基金supported by the National Natural Science Foundation of China(32401919)the Department of Science and Technology of Henan Province(242102111126).
文摘Recent studies have shown that mucilage secretion from aerial roots is an essential feature of modern maize inbred lines,with some retaining the nitrogen-fixing capabilities of ancient landraces.To explore the genetic basis of nitrogen fixation in mucilage and its evolution from teosinte(Zea mays ssp.mexicana)to modern maize,we developed a recombinant inbred line(RIL)population from teosinte and cultivated it under low-nitrogen conditions.Large-scale,multi-year,and multi-environment analyses of RIL-Teo,Doubled Haploid-A(DH-A),Doubled Haploid-B(DH-B),and association populations led to the identification of 15 quantitative trait loci(QTL),68 quantitative trait nucleotides(QTN),and 59 candidate genes linked to mucilage secretion from aerial roots.Functional verification of the candidate gene ZmAco3,which is associated with mucilage secretion in aerial roots,demonstrated that deletion of this gene resulted in a reduction in mucilage secretion in aerial roots.In addition,most maize inbred lines exhibited stronger mucilage secretion from aerial roots under low-nitrogen conditions than under normal-nitrogen conditions.We categorized mucilage secretion into constitutive and low-nitrogen-inducible types.Through genotype-by-environment interaction studies,8 QTL,16 QTN,and 19 candidate genes were identified,revealing the genetic mechanisms underlying mucilage secretion under low-nitrogen conditions.These findings provide a comprehensive genetic analysis of the mucilage-secreting ability of maize aerial roots,contributing to our understanding of nitrogen fixation and offering potential avenues for enhancing nitrogen fixation in modern maize lines.This research advances knowledge of plant nutrient acquisition strategies and has implications for sustainable agricultural practices.
文摘This study compared the control effect of 110 g/L etoxazole SC,15%abamectin·etoxazole SC,30%cyetpyrafen SC,43%bifenazate SC and 1.8%abamectin EC five acaricides sprayed by unmanned aerial vehicle(UAV)on Panonychus citri,aiming to screen out the appropriate acaricide for the control of this pest by UAV spraying.The results showed that 15%abamectin·etoxazole SC and 30%cyetpyrafen SC had the highest control efficacy,which remained above 90%14 d after application.Secondary performance was observed in 43%bifenazate SC and 110 g/L etoxazole SC,which demonstrated enhancing control effect.However,1.8%abamectin EC showed slower effect.Considering the control effect and population reduction rate of P.citri,15%abamectin·etoxazole SC and 30%cyetpyrafen SC were suggested as the effective acaricides for the control of this pest.
