Large Unmanned Aerial Vehicles Research Articles

Durability analysis of large and medium-sized unmanned aerial vehicles based on load spectrum and probabilistic fracture mechanics

The analysis of unmanned aerial vehicle (UAV) durability is crucial for cost-effective repair and maintenance. Assessing the degree of damage and predicting the economic lifespan of a UAV is a critical component of its design and use. To evaluate the durability of large and medium-sized UAVs, data is gathered, and simulations are performed under real-world working conditions. The analysis includes creating a crack growth model for small cracks and determining the distribution of crack sizes, estimating the distribution of Time to Crack Initiation (TTCI), and calculating the general Equivalent Initial Flaw Size (EIFS) distribution. The results obtained from these analyses meet the UAV’s flight hour requirements and help to predict its economic life. This prediction is also beneficial for managing and maintaining the UAV’s life cycle.

Optimisation of Multi-Type Logistics UAV Scheduling under High Demand

At present, interest in the application of unmanned aerial vehicles (UAV) for delivery is growing. A new “multi-type of UAV collaborative delivery” mode has been proposed. Through a combination of large, medium and small UAVs, the delivery capabilities of the UAV logistics system are significantly improved. Sometimes there is high demand, resulting in planned delivery routes that are no longer feasible, and even cause a shortage of distribution centre capacity and drones. This study explores logistics delivery strategies to solve problems caused by high demand. In this study, a multitype and multidistribution UAV model was established with the objective of minimising the total cost of distribution by considering factors such as the UAV energy consumption, load and distribution centre conditions. An improved ant colony algorithm was designed and its effectiveness was verified through the variability of the calculation time and multiple calculation results of different-scale examples. Finally, the classic vehicle routing problem (VRP) case is used in three scenarios to analyse the UAV scheduling optimisation problem. The results indicate that assisted delivery can reduce costs by 3% while ensuring delivery timeliness. The results of this study can provide guidance and benchmarks for the application of UAVs in urban logistics delivery systems.

Knowledge graph completion assisted graph neural network for spectrum resource optimization of UAV swarm

Unmanned aerial vehicles (UAVs) are playing an increasing critical role in industrial, agricultural and military Scenario. However, the energy consuming cannot be ignored, which constrains the flying time and quality of service (QoS), especially in large UAV swarm. In this paper, a knowledge graph completion assisted graph neural network (KGC-GNN) is proposed for UAV swarm aiming at optimizing the spectrum resource to improve the energy efficiency (EE). The proposed network consists of two parts: a graph attention network based on relational coding (GATRC) encoder and a task-oriented decoder based on InteractE model named CP-IE. The further simulation demonstrates that our approach can attain near-optimal spectrum resource optimization scheme with higher energy efficiency and achieve rapid convergence with the channel distribution information (CDI), UAV and environment parameters.

Towards sustainable UAV operations: Balancing economic optimization with environmental and social considerations in path planning

Unmanned Aerial Vehicles (UAVs), i.e., drones, are expected to be widely used in various applications, such as parcel delivery and passenger transport, with the benefits of mitigating traffic congestion and reducing carbon emissions. In this paper, we study a UAV path planning problem under uncertain weather conditions, and design a data-driven dynamic decision support system for multiple types of UAVs. To this end, we categorize all relevant costs into three types, namely, economic, environmental, and social costs, and formulate a nonlinear two-stage stochastic programming model to establish optimal paths for UAV missions under weather uncertainty. We then discretize the nonlinear model and propose a tight linear approximation for the discretized problem to allow for a near real-time implementation. To quantify weather uncertainty, we propose a weather scenario generation algorithm to map ensemble-based weather forecast information to airspace blockage maps. With comprehensive computational studies through simulations, we show that our proposed stochastic approach can lower operating costs by an average of around 6%, where the savings increase as weather conditions become more severe and complex. We also find that, for missions operated by small UAVs, it is not sufficient to determine a path solely based on economic cost minimization, but it should rather be through total cost minimization, which involves environmental and social costs. Considering only the economic cost in the optimization may lead to much higher non-economic costs. However, for missions operated by large UAVs, it is sufficient to determine paths through economic cost optimization, as including environmental and social costs in the optimization process does not result in solutions that are much different from those obtained by considering only the economic costs. For both small and large UAVs, a path established solely through environmental or social cost minimization may not be economically sustainable, as doing so would imply very high economic costs.

Nexus of Deep Reinforcement Learning and Leader–Follower Approach for AIoT Enabled Aerial Networks

The Industrial Internet of Things (IIoT) is a new industrial 4.0 paradigm that combines IoT, robotics, cyber-physical systems, and other future industrial advancements. Unmanned Aerial Vehicles (UAVs), part of the IIoT infrastructure, have a significant potential for civil and military purposes. Through the Artificial Intelligence of Things (AIoT), a well-organized group of UAVs outperforms a single large UAV in terms of device scalability, maintenance, and expense. Therefore, the UAV swarm with industry 4.0 intelligence can be used for a wide range of 24/7 security and remote monitoring applications. Though multi-UAV systems are beneficial, their application has many challenges. There is a high risk of collision in the multi-UAV system without coordination. This paper proposes an AIoT-based Navigation and Formation Control (AIoT-NFC) mechanism to scale down the collision risk by combining Deep Reinforcement Learning (DRL) with the leader-follower approach. In AIoT-NFC, a Deep Deterministic Policy Gradient (DDPG) based algorithm is proposed to navigate UAVs in remote surveillance without colliding with obstacles and other UAVs. Furthermore, the AIoT-NFC system incorporates a fault tolerance mechanism that can handle the scenario of a leader's failure due to actuator malfunction. Experimental results show that the AIoT-NFC achieves faster convergence with a lower collision rate. AIoT-NFC reduced the collision rate by 14.99% compared to existing navigation methods in successful formation without colliding with the other UAVs.

Deep Object Detection of Crop Weeds: Performance of YOLOv7 on a Real Case Dataset from UAV Images

Weeds are a crucial threat to agriculture, and in order to preserve crop productivity, spreading agrochemicals is a common practice with a potential negative impact on the environment. Methods that can support intelligent application are needed. Therefore, identification and mapping is a critical step in performing site-specific weed management. Unmanned aerial vehicle (UAV) data streams are considered the best for weed detection due to the high resolution and flexibility of data acquisition and the spatial explicit dimensions of imagery. However, with the existence of unstructured crop conditions and the high biological variation of weeds, it remains a difficult challenge to generate accurate weed recognition and detection models. Two critical barriers to tackling this challenge are related to (1) a lack of case-specific, large, and comprehensive weed UAV image datasets for the crop of interest, (2) defining the most appropriate computer vision (CV) weed detection models to assess the operationality of detection approaches in real case conditions. Deep Learning (DL) algorithms, appropriately trained to deal with the real case complexity of UAV data in agriculture, can provide valid alternative solutions with respect to standard CV approaches for an accurate weed recognition model. In this framework, this paper first introduces a new weed and crop dataset named Chicory Plant (CP) and then tests state-of-the-art DL algorithms for object detection. A total of 12,113 bounding box annotations were generated to identify weed targets (Mercurialis annua) from more than 3000 RGB images of chicory plantations, collected using a UAV system at various stages of crop and weed growth. Deep weed object detection was conducted by testing the most recent You Only Look Once version 7 (YOLOv7) on both the CP and publicly available datasets (Lincoln beet (LB)), for which a previous version of YOLO was used to map weeds and crops. The YOLOv7 results obtained for the CP dataset were encouraging, outperforming the other YOLO variants by producing value metrics of 56.6%, 62.1%, and 61.3% for the mAP@0.5 scores, recall, and precision, respectively. Furthermore, the YOLOv7 model applied to the LB dataset surpassed the existing published results by increasing the mAP@0.5 scores from 51% to 61%, 67.5% to 74.1%, and 34.6% to 48% for the total mAP, mAP for weeds, and mAP for sugar beets, respectively. This study illustrates the potential of the YOLOv7 model for weed detection but remarks on the fundamental needs of large-scale, annotated weed datasets to develop and evaluate models in real-case field circumstances.

Architecture of Emergency Communication Systems in Disasters through UAVs in 5G and Beyond

Unmanned aerial vehicles (UAVs) are valued in 5G and 6G networks due to their communication capabilities, low cost, and flexible deployment. Recently, UAV-aided emergency networks in disasters have been designed where one single large UAV is used. Compared with a single large UAV, Flying Ad Hoc Networks (FANETs) with small UAVs have many benefits. Therefore, instead of a single large UAV, a FANET is proposed in this paper. To take full advantage of their services, UAVs must be able to communicate efficiently with each other and with existing networking infrastructures. However, high node mobility is one of the main characteristics of FANETs, which can result in rapid topology changes with frequent link breakage and unstable communications that cause collision and packet loss. As an alternative, networks can be broken up into smaller groups or clusters to control their topology efficiently and reduce channel contention. In this study, a novel cluster-based mechanism is proposed for FANETs. The process of cluster management is described. The IEEE 802.11 backoff method is specifically intended for direct communications and is not appropriate for cluster-based communications. Therefore, a new backoff mechanism is proposed based on cluster size to optimize performance. An analytical study using the Markov chain model is presented to explore the performance of the proposed mechanism. The study takes into account Nakagami-m fading channels. Performance-influencing parameters are taken into consideration and the relationships among these parameters as well as performance metrics such as throughput, packet dropping rate, outage probability, and delay are obtained. Furthermore, simulation results are provided which verify the analytical studies. A quantitative comparison with current cluster-based methods is also presented. The simulation results show that the suggested technique enhances system performance and complies with the safety message delay constraint of 100 ms.

From laboratory to in-situ 3D measurements of complex pollution states in the city: Introducing a general concept using compact multisensory assemblies on UAVs

In the city, it is still a challenge to implement a mobile measurement device to accurately monitor its complex pollution state. Current research proposes new technological developments and many studies implement an Unmanned Aerial Vehicle (UAV)-based platforms. However, many questions arise on the representativeness of such measurements and on the UAV impact on data quality. Here, UAV is used to link between sparsely located ground monitoring sites and lidar station measuring pollution, the latter of which are at heights of typically >200 m. Information at intermediate heights are missing but needed for health studies and also for lidar validation algorithms. In this regard, we propose and demonstrate a UAV-based platform aimed at measuring meteorological and air quality parameters, namely, air temperature (Tair), relative humidity (RH) and PM2.5 (Particulate matter pollution with a diameter of less than 2.5 μm) on both compact and large UAV integrations. Each integration was separately investigated both numerically and experimentally in terms of the possible set of instruments used in the setup. In particular, custom-made meteorological shelters were constructed and tested in the laboratory under different propeller conditions. The best placement locations on the UAVs were verified using numerical airflow simulations employing real UAV geometries. Next, we compared between different sensors for Tair on a diurnal cycle and deduced the best work time corresponding to minimal impact of the outside conditions (mainly due to direct sun exposure). The influence of propeller rotation on measured parameters has been studied in detail. In addition, a pilot field experiment was conducted in the urban domain using our platform and these measurements were compared to all available data sources. Our field experiment indicated a mixed local pollution layer up to 300 m. Finally, we suggest a practical guideline for carrying out field experiments employing both UAVs. We have also considered the fact that wide use of UAV technologies in crowded cities in the context presented in this paper is currently restricted by regulations and privacy that vary among different countries.

Extraction of Micro-Doppler Feature Using LMD Algorithm Combined Supplement Feature for UAVs and Birds Classification

In the past few decades, the demand for reliable and robust systems capable of monitoring unmanned aerial vehicles (UAVs) increased significantly due to the security threats from its wide applications. During UAVs surveillance, birds are a typical confuser target. Therefore, discriminating UAVs from birds is critical for successful non-cooperative UAVs surveillance. Micro-Doppler signature (m-DS) reflects the scattering characteristics of micro-motion targets and has been utilized for many radar automatic target recognition (RATR) tasks. In this paper, the authors deploy local mean decomposition (LMD) to separate the m-DS of the micro-motion parts from the body returns of the UAVs and birds. After the separation, rotating parts will be obtained without the interference of the body components, and the m-DS features can also be revealed more clearly, which is conducive to feature extraction. What is more, there are some problems in using m-DS only for target classification. Firstly, extracting only m-DS features makes incomplete use of information in the spectrogram. Secondly, m-DS can be observed only for metal rotor UAVs, or large UAVs when they are closer to the radar. Lastly, m-DS cannot be observed when the size of the birds is small, or when it is gliding. The authors thus propose an algorithm for RATR of UAVs and interfering targets under a new system of L band staring radar. In this algorithm, to make full use of the information in the spectrogram and supplement the information in exceptional situations, m-DS, movement, and energy aggregation features of the target are extracted from the spectrogram. On the benchmark dataset, the proposed algorithm demonstrates a better performance than the state-of-the-art algorithms. More specifically, the equal error rate (EER) proposed is 2.56% lower than the existing methods, which demonstrates the effectiveness of the proposed algorithm.

A Fast and Robust Algorithm with Reinforcement Learning for Large UAV Cluster Mission Planning

Large Unmanned Aerial Vehicle (UAV) clusters, containing hundreds of UAVs, have widely been used in the modern world. Therein, mission planning is the core of large UAV cluster collaborative systems. In this paper, we propose a mission planning method by introducing the Simple Attention Model (SAM) into Dynamic Information Reinforcement Learning (DIRL), named DIRL-SAM. To reduce the computational complexity of the original attention model, we derive the SAM with a lightweight interactive model to rapidly extract high-dimensional features of the cluster information. In DIRL, dynamic training conditions are considered to simulate different mission environments. Meanwhile, the data expansion in DIRL guarantees the convergence of the model in these dynamic environments, which improves the robustness of the algorithm. Finally, the simulation experiment results show that the proposed method can adaptively provide feasible mission planning schemes with second-level solution speed and that it exhibits excellent generalization performance in large-scale cluster planning problems.

Integration of software defined radio on an unmanned aerial vehicle

The current market does not provide commercially available products of modular radios for unmanned aerial vehicles (UAVs). The goal of the project presented in this paper is to improve the usability of technology related to the functions provided by software-defined radios (SDRs) and UAVs, especially for radio frequency spectrum monitoring, migration and border control. The project focuses on integrating SDRs with UAVs, reception sensitivity, directional antennas, the precision of signal localization, and footprint reduction. The conducted activities resulted in a functional prototype of a large UAV, capable of carrying various equipment, and successful integration of SDR with the built UAV. This paper focuses on the technical aspect of integration between the two systems and their interoperability. Further, it provides an overview of the operational possibilities and limitations of the integrated systems.

A Study of 3D Printed Box Structure

Unmanned Aerial Vehicles (UAV) are commonly used for surveillance and aerial mapping. Balsa wood construction is common for small UAV. However, for larger UAV size, balsa construction can be too fragile. 3D printing based airframe can help in producing accurate profile contour needed in a wing design, particularly on Blended Wing Body (BWB) design. Nowadays, 3D printing machines are not expensive and easily available. Flight Technology and Test Centre (FTTC) RIG, Universiti Teknologi MARA (UiTM) has been developing and building small BWB UAV made of 3D printing. At the moment, the strength and stiffness of the wing box structure has not been properly investigated. The general target of this research is to understand the static mechanical behavior of a small wing box suitable for UAV manufactured by 3D printing. A simple wing box that can be produced on in-house 3D printer was produced. Standard tensile test was conducted to the PLA (Polylactic Acid) printed material. Finite element simulation of the wing box was performed, and static test experiment was conducted. Stresses and displacements were obtained and analyzed.

An Operational Safety Evaluation Method for Manned Transport Aircraft and Large UAV in Mixed Airspace

To improve the predictive ability in trajectory of large unmanned aerial vehicle (UAV) and the calculation performance in complicated circumstances with mixed airspace, multiple aircraft types, and joint operations, the concept of phased trajectory deviation (PTD) is introduced and a corresponding minimal interval algorithm (PTD-MI) is set up. This algorithm is capable of deriving the minimal interval between various aircraft types according to the crosswind impacts and the UAV characteristics at different flight phases and thus achieves the effective safety evaluation in airspace operation. To demonstrate the rationality and generality of the proposed algorithm, several simulation experiments are conducted. Based on the experimental results, flight procedure protection area is plotted by PTD-MI algorithm and compared with that generated by Ground-Based Augmentation System (GBAS). Results indicate that the proposed algorithm is capable of deriving a more scientific basis for airspace assignment and outperform GBAS in dealing with wide-area space problems. And, compared with GBAS, PTD-MI algorithm shows a more stable calculation performance and is easier to output the results. PTD-MI algorithm is proposed under the flight safety regulation designed by the International Civil Aviation Organization (ICAO) and designed to provide effective technical supports for the safe and normal operations of aircrafts.

Comprehensive Marine Observing Experiment Based on High-Altitude Large Unmanned Aerial Vehicle (South China Sea Experiment 2020 of the “Petrel Project”)

In collaboration with 12 other institutions, the Meteorological Observation Center of the China Meteorological Administration undertook a comprehensive marine observation experiment in the South China Sea using the Yilong-10 high-altitude large unmanned aerial vehicle (UAV). The Yilong-10 UAV carried a self-developed dropsonde system and a millimeter-wave cloud radar system. In addition, a solar-powered unmanned surface vessel and two drifting buoys were used. The experiment was further supported by an intelligent, reciprocating horizontal drifting radiosonde system that was deployed from the Sansha Meteorological Observing Station, with the intent of producing a stereoscopic observation over the South China Sea. Comprehensive three-dimensional observations were collected using the system from 31 July to 2 August, 2020. This information was used to investigate the formation and development processes of Typhoon Sinlaku (2020). The data contain measurements of 21 oceanic and meteorological parameters acquired by the five devices, along with video footage from the UAV. The data proved very helpful in determining the actual location and intensity of Typhoon Sinlaku (2020). The experiment demonstrates the feasibility of using a high-altitude, large UAV to fill in the gaps between operational meteorological observations of marine areas and typhoons near China, and marks a milestone for the use of such data for analyzing the structure and impact of a typhoon in the South China Sea. It also demonstrates the potential for establishing operational UAV meteorological observing systems in the future, and the assimilation of such data into numerical weather prediction models.

Air Particle Separator for Unmanned Aerial Vehicles with Combustion Engines

Although a significant portion of unmanned aerial vehicles (UAVs) rely entirely on batteries, there are larger UAVs that operate by utilizing internal combustion engines. These special aircrafts ingest vast quantities of air, directly feeding the supply into the engine for combustion. The goal is to design and build an engine air particle separator (EAPS) for UAVs that employ combustion engines, to remove sand, dust, dirt, or any fine particles from the air being supplied to the engine. Although there are many constraints and restrictions to be considered, it is desired for the EAPS to be a single component, have the ability to connect to a specified intake collar, and fit within a given volume. Among other elements considered, the efficiency, pressure drop, areas of failure, and the selection of a material to build the separator were factored. Three methods of particle filtering were selected: inertial, centrifugal, and hypothetical pressure-barrier separation. To accomplish these goals, the principles of inertia, centrifugal forces, and pressure changes were used along with additive manufacturing – to be able to design and build complex geometries. Results were based on the three prototypes that were built and tested in an enclosure simulating the harsh weather environment and the force applied by the internal combustion engine from the UAV. These results showed that a centrifugal design was best suited for the purpose of the experiment with an experimental efficiency of 87% of the particles being separated from the air.

Learning to Fly: A Distributed Deep Reinforcement Learning Framework for Software-Defined UAV Network Control

Control and performance optimization of wireless networks of Unmanned Aerial Vehicles (UAVs) require scalable approaches that go beyond architectures based on centralized network controllers. At the same time, the performance of model-based optimization approaches is often limited by the accuracy of the approximations and relaxations necessary to solve the UAV network control problem through convex optimization or similar techniques, and by the accuracy of the channel network models used. To address these challenges, this article introduces a new architectural framework to control and optimize UAV networks based on Deep Reinforcement Learning (DRL). Furthermore, it proposes a virtualized, `ready-to-fly' emulation environment to generate the extensive wireless data traces necessary to train DRL algorithms, which are notoriously hard to generate and collect on battery-powered UAV networks. The training environment integrates previously developed wireless protocol stacks for UAVs into the CORE/EMANE emulation tool. Our `ready-to-fly' virtual environment guarantees scalable collection of high-fidelity wireless traces that can be used to train DRL agents. The proposed DRL architecture enables distributed data-driven optimization (with up to 3.7 × throughput improvement and 0.2 × latency reduction in reported experiments), facilitates network reconfiguration, and provides a scalable solution for large UAV networks.

Radar Surveillance of Unmanned Aerial Vehicles (Review)

Radar surveillance of unmanned aerial vehicles (UAVs) is actively developing area of scientific research. This article provides a review and analysis of publications in recent years devoted to the methods and radar systems of detection and recognition of classes and types of UAVs. It is noted that the most difficult targets for radar detection are low-sized, low-speed small UAVs (drones) flying at low and extremely low altitudes. If large and medium-sized UAVs can be detected by modern radar systems, then for the detection of small UAVs it is advisable to create specialized highly efficient, highly mobile, portable and inexpensive active UAV detection radars. The technical requirements for such radars are defined and recommendations for their implementation are provided. High-performance protection systems based on adaptive lattice filters are offered to protect UAV detection radars from noise jamming and passive interference. It is shown that the research on the methods of recognizing UAV classes and types is a development of the existing theory and technology of radar recognition of air targets.

A Review on Communications Perspective of Flying Ad-Hoc Networks: Key Enabling Wireless Technologies, Applications, Challenges and Open Research Topics

Unmanned aerial vehicles (UAVs), also known as drones, once centric to military applications, are presently finding their way in many civilian and commercial applications. If national legislations permit UAVs to operate autonomously, one will see the skies become populated with many small UAVs, each one performing various tasks such as mail and package delivery, traffic monitoring, event filming, surveillance, search and rescue, and other applications. Thus, advancing to multiple small UAVs from a single large UAV has resulted in a new clan of networks known as flying ad-hoc networks (FANETs). Such networks provide reliability, ease of deployment, and relatively low operating costs by offering a robust communication network among the UAVs and base stations (BS). Although FANETs offer many benefits, there also exist a number of challenges that need to be addressed; the most significant of these being the communication one. Therefore, the article aims to provide insights into the key enabling communication technologies through the investigation of data rate, spectrum type, coverage, and latency. Moreover, application scenarios along with the feasibility of key enabling technologies are also examined. Finally, challenges and open research topics are discussed to further hone the research work.

Multi-Scale and Occlusion Aware Network for Vehicle Detection and Segmentation on UAV Aerial Images

With the advantage of high maneuverability, Unmanned Aerial Vehicles (UAVs) have been widely deployed in vehicle monitoring and controlling. However, processing the images captured by UAV for the extracting vehicle information is hindered by some challenges including arbitrary orientations, huge scale variations and partial occlusion. In seeking to address these challenges, we propose a novel Multi-Scale and Occlusion Aware Network (MSOA-Net) for UAV based vehicle segmentation, which consists of two parts including a Multi-Scale Feature Adaptive Fusion Network (MSFAF-Net) and a Regional Attention based Triple Head Network (RATH-Net). In MSFAF-Net, a self-adaptive feature fusion module is proposed, which can adaptively aggregate hierarchical feature maps from multiple levels to help Feature Pyramid Network (FPN) deal with the scale change of vehicles. The RATH-Net with a self-attention mechanism is proposed to guide the location-sensitive sub-networks to enhance the vehicle of interest and suppress background noise caused by occlusions. In this study, we release a large comprehensive UAV based vehicle segmentation dataset (UVSD), which is the first public dataset for UAV based vehicle detection and segmentation. Experiments are conducted on the challenging UVSD dataset. Experimental results show that the proposed method is efficient in detecting and segmenting vehicles, and outperforms the compared state-of-the-art works.

Design of High-Power Dual-Redundancy Electro-Mechanical Actuator for Scout and Strike UAV

As the technology advance of UAV (Unmanned Aerial Vehicle), the large UAV is a prevalent trend, which is widely used for scout and strike in modern military battlefield. The flight safety is rather important because of the cost increase of UAV with various airborne devices equipped. EMA (Electromechanical Actuator) is one of the key components in UAV system. Whether its performance is reliable or not determines the flight safety. In this paper, in order to design high-power EMA for scout and strike UAV with fast response and high stability to ensure UAV safety, dual-redundancy technology is adopted. There are two communication interfaces between the actuator and the flight mission computer. The control circuit and the drive circuit are in the form of dual redundancy, while there are two sets of windings in the motor. The controller and actuator design are introduced in details one by one. Also, the paper presents the dual-redundancy design scheme. Several ground tests simulating the real flight conditions are conducted, proving that the EMA design is feasible and its performance is satisfactory. The UAV flight tests are needed later in the future to verify EMA performance in practice.