Search Results (1,355)

The multi-UAV task assignment problem in large-scale group-to-group interception scenarios presents challenges in terms of large computational complexity and the lack of accurate evaluation models. This paper proposes an effective evaluation model and hierarchical task assignment framework to address these challenges. The evaluation model incorporates the dynamics constraints specific to fixed-wing UAVs and improves the Apollonius circle model to accurately describe the cooperative interception effectiveness of multiple UAVs. By evaluating the interception effectiveness during the interception process, the assignment scheme of the multiple UAVs could be given based on the model. To optimize the configuration of UAVs and targets, a hierarchical framework based on the network flow algorithm is employed. This framework utilizes a clustering method based on feature similarity and interception advantage to decompose the large-scale task assignment problem into smaller, complete submodels. Following the assignment, Dubins curves are planned to the optimal interception points, ensuring the effectiveness of the interception task. Simulation results demonstrate the feasibility and effectiveness of the proposed scheme. With the increase in the model scale, the proposed scheme has a greater descending rate of runtime. In a large-scale scenario involving 200 UAVs and 100 targets, the runtime is reduced by $84.86\%$. Full article

Opium poppy is a medicinal plant, and its cultivation is illegal without legal approval in China. Unmanned aerial vehicle (UAV) is an effective tool for monitoring illegal poppy cultivation. However, targets often appear occluded and confused, and it is difficult for existing detectors to accurately detect poppies. To address this problem, we propose an opium poppy detection network, YOLOHLA, for UAV remote sensing images. Specifically, we propose a new attention module that uses two branches to extract features at different scales. To enhance generalization capabilities, we introduce a learning strategy that involves iterative learning, where challenging samples are identified and the model’s representation capacity is enhanced using prior knowledge. Furthermore, we propose a lightweight model (YOLOHLA-tiny) using YOLOHLA based on structured model pruning, which can be better deployed on low-power embedded platforms. To evaluate the detection performance of the proposed method, we collect a UAV remote sensing image poppy dataset. The experimental results show that the proposed YOLOHLA model achieves better detection performance and faster execution speed than existing models. Our method achieves a mean average precision (mAP) of 88.2% and an F1 score of 85.5% for opium poppy detection. The proposed lightweight model achieves an inference speed of 172 frames per second (FPS) on embedded platforms. The experimental results showcase the practical applicability of the proposed poppy object detection method for real-time detection of poppy targets on UAV platforms. Full article

Visual navigation based on image matching has become one of the most important research fields for UAVs to achieve autonomous navigation, because of its low cost, strong anti-jamming ability, and high performance. Currently, numerous positioning and navigation methods based on visual information have been proposed for UAV navigation. However, the appearance, shape, color, and texture of objects can change significantly due to different lighting conditions, shadows, and surface coverage during different seasons, such as vegetation cover in summer or ice and snow cover in winter. These changes pose greater challenges for feature-based image matching methods. This encouraged us to overcome the limitations of previous works, which did not consider significant seasonal changes such as snow-covered UAV aerial images, by proposing an image matching method using season-changing UAV aerial images and satellite imagery. Following the pipeline of a two-channel deep convolutional neural network, we first pre-scaled the UAV aerial images, ensuring that the UAV aerial images and satellite imagery had the same ground sampling distance. Then, we introduced attention mechanisms to provide additional supervision for both low-level local features and high-level global features, resulting in a new season-specific feature representation. The similarity between image patches was calculated using a similarity measurement layer composed of two fully connected layers. Subsequently, we conducted template matching to estimate the UAV matching position with the highest similarity. Finally, we validated our proposed method on both synthetic and real UAV aerial image datasets, and conducted direct comparisons with previous popular works. The experimental results demonstrated that our method achieved the highest matching accuracy on multi-temporal and multi-season images. Full article

A robust controller for the waypoint tracking of a quadrotor unmanned aerial vehicle (UAV) is proposed in this paper, in which position control and attitude control are effectively decoupled. Model predictive control (MPC) is employed in the position controller. The constraints of motors are imposed on the state and input variables of the optimization equation. This design effectively mitigates the nonlinearity of the attitude loop and enhances the planning efficiency of the position controller. The attitude controller is designed using a nonlinear and robust control law based on $SO(3)$ space, which enables continuous control on the $SO(3)$ manifold. By extending the differential flatness of the quadrotor-UAV to the angular acceleration level, the mapping of the control reference from the position controller to the attitude controller is achieved. Simulations are carried out to demonstrate the capability of the proposed controller. In the simulations, multiple aggressive flight trajectories and severe external disturbances are designed. The results show that the controller is robust, with superior accuracy in tracking aggressive trajectories. Full article

Advanced Air Mobility (AAM) is a promising field of services based on Unmanned Aerial Vehicles (UAVs), which aims to provide people and cargo transportation services in underserved areas. The recent advancements in the fields of aviation and mobile telecommunication networks have opened up multiple opportunities for the development of disruptive AAM applications. This paper presents the overview and identifies the major requirements of emerging AAM use cases to confront them with the features provided by the 5G System (5GS), which is commonly considered the key enabler in providing commercial AAM services. The major benefits, gaps, and issues regarding using 5GS to serve AAM operations are identified and discussed. Finally, the future perspectives for AAM services are outlined with a focus on the potential benefit that can be provided as the mobile network evolves towards 6G. Full article

Unmanned aircraft vehicles (UAVs) are now used to support security precautions in search and rescue operations to track and evaluate critical services, to provide cybersecurity measures by transporting security supply chain management (SCM) to sports events, and to aid efforts to safeguard the spectators from attacks. A drone may quickly fly over sports grounds, scan the area for potential dangers, and offer aerial footage and still photographs. Although UAVs provide benefits to their operators, there is a possibility that they may also pose cybersecurity threats. This guide offers recommendations for best security practices, intending to assist sports operators in protecting their networks, materials, and staff for Qatar’s mega sporting events. The literature comprises several theoretical frameworks and conceptual models for security supply chains. Unfortunately, there is no practical model for measuring the behavioral intentions of professional IT and security experts. Therefore, this study conducted research in two stages. In the first stage, an in-depth systematic literature review was conducted to identify the factors and themes of UAV-based SCM for security measures. In the second phase, a survey questionnaire (N = 712) was implemented, comprising the themes and items from the literature review among professional IT and security experts. Exploratory factor analysis (EFA) was carried out with IBM SPSS, and confirmatory factor analysis (CFA) was employed with IBM AMOS. This study proposed and developed a UAV-based SCM model to provide security for Qatar’s mega sporting events, which comprised five factors: traceability, security and privacy, trust, acceptability, and preparedness. This study also confirmed the validity and reliability of the newly developed scales, offering practical and proposed implications for the IT and security industries. The key findings of the study are: (1) a valid and reliable UAV-based cybersecurity framework for FIFA mega sporting events was developed; (2) five critical factors were identified, including traceability, security and privacy, trust, acceptability, and preparedness; (3) all factors were significantly and positively correlated, highlighting the complexity of managing security systems in mega sporting events. Full article

This paper introduces a location–allocation model to support environmental emergency response strategic planning using a drone-based network. Drones are used to verify potential emergencies, gathering additional information to support emergency response missions when time and resources are limited. The resulting discrete facility location–allocation model with mobile servers assumes a centralized network operated out of sight by first responders and government agents. The optimization problem seeks to find the minimal cost configuration that meets operational constraints and performance objectives. To test the practical applicability of the proposed model, a real-life case study was implemented for the municipality of Ji-Paraná, in the Brazilian Amazon, using demand data from a mobile whistle-blower application and from satellite imagery projects that monitor deforestation and fire incidents in the region. Experiments are performed to understand the model’s sensitivity to various demand scenarios and capacity restrictions. Full article

High water levels near railway tracks can be a major factor affecting the safety of train passage. Water conditions near the tracks are normally monitored through visual inspections. However, this method is limited in spatial coverage and may not provide comparable information over time. We evaluated the utility of satellite imagery (Planet Dove constellation at 3 m pixel size) at the landscape level to assess overall water surface area along railway tracks. Comparatively, we evaluated the use of Structure- from-Motion 3D point clouds and high spatial detail orthomosaics (3 cm) generated from a commercial off-the-shelf Unmanned Aerial System (UAS) (DJI M300 RTK) for measuring vertical water level changes and extent of surface water, respectively, within the right-of-way of a railway line in Ontario, Canada, in areas prone to high water level and flooding. Test sites of varied lengths (~180 m to 500 m), were assessed four times between June and October 2021. Our results indicate that the satellite imagery provides a large-scale overview regarding the extent of open water in wetlands at long distances from the railway tracks. Analysis of the UAS derived 3D point cloud indicates that changes in water level can be determined at the centimeter scale. Furthermore, the spatial error (horizontal and vertical alignments) between the multi-temporal UAS data collections between sites was less than 3 cm. Our research highlights the importance of using consistent UAS data collection protocols, and the significant potential of commercial off-the-shelf UAS systems for water level monitoring along railway tracks. Full article

The current morphing technologies are mostly regarded as auxiliary tools, providing additional control torques to enhance the flight maneuverability of unmanned aerial vehicles (UAVs), and they cannot exist independently of the traditional control surfaces. In this paper, we propose a tandem-wing micro aerial vehicle (MAV) with multiple variable-sweep wings, which can reduce the additional inertia forces and moments and weaken the dynamic coupling between longitudinal and lateral motion while the MAV morphs symmetrically for pitch control or asymmetrically for roll control, thereby flying without the traditional aileron and elevator. First, load experiments were conducted on the MAV to verify the structural strength of the multiple variable sweep wings, and the control moments caused by the morphing of the MAV were presented through numerical simulations. Then, the effects caused by symmetric and asymmetric morphing were investigated via dynamic response simulations based on the Kane dynamic model of the MAV, and the generated additional inertia forces and moments were also analyzed during morphing. Finally, dynamic response experiments and open-loop flight experiments were conducted. The experimental results demonstrated that the morphing mode in this study could weaken the coupling between the longitudinal and lateral dynamics and that it was feasible for attitude control without the traditional aileron and elevator while flying. Full article

Aerial manipulation aims to combine the versatility and the agility of aerial platforms with the manipulation capabilities of robotic arms. Their fast deployment allows for their implementation in maintenance tasks and support during disaster situations. However, the under-actuated nature of multirotor UAVs limits the magnitude and direction of the forces an aerial vehicle can safely exert during manipulation tasks. In this paper, the problems associated with UAVs and torsional tasks constraints regarding valve turning are addressed. An add-on thrust vectoring device which enhances manipulation options available to a conventional multirotor UAV is developed and described. The proposed system allows for a partial decoupling of the attitude and velocity vector of a multirotor. This permits stable translational flight and higher torque capabilities for torsional tasks. The separation of attitude and the velocity vector that allows for the design of a passive mechanism for valve operation is presented in this paper as well. The experimental results illustrate the forces and torques that can be generated in the evaluated operation modes. Full article

Accurate obstacle detection plays a crucial role in the creation of high-precision maps within unstructured terrain environments, as it supplies vital decision-making information for unmanned engineering vehicles. Existing works primarily focus on the semantic segmentation of terrain environments, overlooking the safety aspect of vehicle driving. This paper presents a hazardous obstacle detection framework in addition to driving safety-assured semantic information in the generated high-precision map of unstructured scenarios. The framework encompasses the following key steps. Firstly, a continuous terrain point cloud model is obtained, and a pre-processing algorithm is designed to filter noise and fill holes in the point cloud dataset. The Sobel-G operator is then utilized to establish a digital gradient model, facilitating the labeling of hazardous obstacles. Secondly, a bidirectional long short-term memory (Bi-LSTM) neural network is trained on obstacle categories. Finally, by considering the geometric driving state of the vehicle, obstacles that pose safety risks to the vehicle are accurately extracted. The proposed algorithm is validated through experiments conducted on existing datasets as well as real, unstructured terrain point clouds reconstructed by drones. The experimental results affirm the accuracy and feasibility of the proposed algorithm for obstacle information extraction in unstructured scenes. Full article

Despite the growing demand for unmanned aerial vehicles (UAVs), the use of conventional UAVs is limited, as most of them require being remotely operated by a person who is not within the vehicle’s field of view. Recently, many studies have introduced reinforcement learning (RL) to address hurdles for the autonomous flight of UAVs. However, most previous studies have assumed overly simplified environments, and thus, they cannot be applied to real-world UAV operation scenarios. To address the limitations of previous studies, we propose a stepwise soft actor–critic (SeSAC) algorithm for efficient learning in a continuous state and action space environment. SeSAC aims to overcome the inefficiency of learning caused by attempting challenging tasks from the beginning. Instead, it starts with easier missions and gradually increases the difficulty level during training, ultimately achieving the final goal. We also control a learning hyperparameter of the soft actor–critic algorithm and implement a positive buffer mechanism during training to enhance learning effectiveness. Our proposed algorithm was verified in a six-degree-of-freedom (DOF) flight environment with high-dimensional state and action spaces. The experimental results demonstrate that the proposed algorithm successfully completed missions in two challenging scenarios, one for disaster management and another for counter-terrorism missions, while surpassing the performance of other baseline approaches. Full article

The vertical take-off and landing (VTOL) of unmanned aerial vehicles (UAVs) is extensively employed in various sectors. To ensure adherence to design specifications and mission requirements, it is vital to verify flight control and system performance using an accurate dynamic model specific to UAV configuration. Traditionally, engineers follow a sequential approach in UAV design, which involves multiple design iterations comprising CAD drawings, material collection, fabrication, flight tests, system identification, modifications, dynamic model extraction, checking if the results meet requirements, and then repeating the process. However, as UAVs become larger, heavier, and more enduring to meet complex system demands, the costs and time associated with each design iteration of creating a new UAV escalate exponentially. The bare-airframe dynamics of the UAV are crucial for engineers to design a controller and validate handling quality and performance. This paper proposes a novel method to accurately predict the dynamic model of the bare airframe for quadrotor UAVs without physically constructing them in the real world. The core concept revolves around converting the quadrotor UAV design from CAD software into a UAV model within an X-Plane simulator. Leveraging the CIFER software’s two key features—frequency domain system identification and parametric model fitting—the unstable bare-airframe dynamics are extracted for both the UAV model in X-Plane and a real-world DJI 450 UAV with the same physical configuration. This paper provides essential parameters and guidance for constructing a 92% high-fidelity dynamic model of the given UAV configuration in X-Plane. The flight test results demonstrate excellent alignment with the simulation outcomes, instilling confidence in the effectiveness of the proposed method for designing and validating new UAVs. Moreover, this approach significantly reduces the time and cost associated with the traditional design process, which requires an actual build of the UAV and many flight tests to verify the performance. Full article

The rubber tree (Hevea brasiliensis) is an important tree species for the production of natural latex, which is an essential raw material for varieties of industrial and non-industrial products. Rapid and accurate identification of the number of rubber trees not only plays an important role in predicting biomass and yield but also is beneficial to estimating carbon sinks and promoting the sustainable development of rubber plantations. However, the existing recognition methods based on canopy characteristic segmentation are not suitable for detecting individual rubber trees due to their high canopy coverage and similar crown structure. Fortunately, rubber trees have a defoliation period of about 40 days, which makes their trunks clearly visible in high-resolution RGB images. Therefore, this study employed an unmanned aerial vehicle (UAV) equipped with an RGB camera to acquire high-resolution images of rubber plantations from three observation angles (−90°, −60°, 45°) and two flight directions (SN: perpendicular to the rubber planting row, and WE: parallel to rubber planting rows) during the deciduous period. Four convolutional neural networks (multi-scale attention network, MAnet; Unet++; Unet; pyramid scene parsing network, PSPnet) were utilized to explore observation angles and directions beneficial for rubber tree trunk identification and counting. The results indicate that Unet++ achieved the best recognition accuracy (precision = 0.979, recall = 0.919, F-measure = 94.7%) with an observation angle of −60° and flight mode of SN among the four deep learning algorithms. This research provides a new idea for tree trunk identification by multi-angle observation of forests in specific phenological periods. Full article

This study investigates the application of unoccupied aerial vehicles (UAVs) equipped with a Micasense RedEdge-MX multispectral camera for the estimation of Secchi depth (SD) in inland water bodies. The research analyzed and compared five sun-glint correction methodologies—Hedley, Goodman, Lyzenga, Joyce, and threshold-removed glint—to model the SD values derived from UAV multispectral imagery, highlighting the role of reflectance accuracy and algorithmic precision in SD modeling. While Goodman’s method showed a higher correlation (0.92) with in situ SD measurements, Hedley’s method exhibited the smallest average deviation (0.65 m), suggesting its potential in water resource management, environmental monitoring, and ecological modeling. The study also underscored the quasi-analytical algorithm (QAA) potential in estimating SD due to its flexibility to process data from various sensors without requiring in situ measurements, offering scalability for large-scale water quality surveys. The accuracy of SD measures calculated using QAA was related to variability in water constituents of colored dissolved organic matter and the solar zenith angle. A practical workflow for SD acquisition using UAVs and multispectral data is proposed for monitoring inland water bodies. Full article