Deployment Of Drones Research Articles

Dynamic behavior recognition in aerial deployment of multi-segmented foldable-wing drones using variational autoencoders

Dynamic behavior recognition in aerial deployment of multi-segmented foldable-wing drones using variational autoencoders

Request prompt response in same-day delivery problem with drone resupply

The present research considers the request for prompt response in the same-day delivery (SDD) problem with drone resupply. SDD has gained popularity since customer satisfaction is highly valued in the logistics industry. Customers, even those residing far from distribution centres, anticipate the opportunity to get prompt responses. The decision-maker (DM) promptly decides whether to accept the order or not as customers’ requests stochastically occur throughout the day. We assume that the truck promises to deliver packages within the promised time while a drone performs multiple trips from the warehouse to replenish the truck at any required time. A novel Deep Q-Learning (DQL) approach is proposed to maximise the acceptance rate of requests and simultaneously ensure prompt responses. Two nested agents are utilised to (a) determine order acceptance and (b) dynamically adjust drone deployment based upon its availability. Comprehensive testing and analysis demonstrate the superior effectiveness of our approach compared to benchmarks. Findings suggest that: (1) Drone resupply enables SDD to remote customers within designated distances; (2) Deep Q-learning optimises drone’s waiting times to dynamically adjust payload capacity; and (3) it is the increase in resupply frequency rather than payload size per resupply that more effectively improve the whole delivery volume.

Drone-Based Wildfire Detection with Multi-Sensor Integration

Wildfires pose a severe threat to ecological systems, human life, and infrastructure, making early detection critical for timely intervention. Traditional fire detection systems rely heavily on single-sensor approaches and are often hindered by environmental conditions such as smoke, fog, or nighttime scenarios. This paper proposes Adaptive Multi-Sensor Oriented Object Detection with Space–Frequency Selective Convolution (AMSO-SFS), a novel deep learning-based model optimized for drone-based wildfire and smoke detection. AMSO-SFS combines optical, infrared, and Synthetic Aperture Radar (SAR) data to detect fire and smoke under varied visibility conditions. The model introduces a Space–Frequency Selective Convolution (SFS-Conv) module to enhance the discriminative capacity of features in both spatial and frequency domains. Furthermore, AMSO-SFS utilizes weakly supervised learning and adaptive scale and angle detection to identify fire and smoke regions with minimal labeled data. Extensive experiments show that the proposed model outperforms current state-of-the-art (SoTA) models, achieving robust detection performance while maintaining computational efficiency, making it suitable for real-time drone deployment.

Flying books: a new frontier of mobile libraries in the era of Fifth Industrial Revolution (5IR)

Purpose The purpose of this study is to explore how drone technology can enhance the reach and efficiency of mobile library services, particularly in remote and underserved areas. It aims to evaluate the potential of drones in overcoming traditional access barriers, improving resource distribution and fostering greater community engagement through advanced service delivery mechanisms. Design/methodology/approach The study uses a qualitative approach to explore the integration of drone technology in mobile library services, framed within the context of the Fifth Industrial Revolution (5IR). Drawing literature from databases such as Google Scholar, ResearchGate and Scopus, it also presents a case study of drone-enabled library services implemented in rural communities of Nigeria. The study focuses on the practical aspects of drone deployment, the impact on underserved communities and the challenges faced, offering insights into the logistical and operational dynamics of this innovative service model. Findings The study reveals that drone technology significantly improves access to library resources, particularly in hard-to-reach and disaster-prone areas. Drones offer an eco-friendly, cost-effective alternative to conventional mobile libraries, cutting operational costs by 60% and reducing delivery times by 40%. Despite these advantages, the implementation process encountered challenges such as financial sustainability, community skepticism and the need for specialized staff training. Originality/value The study contributes to the evolving discourse on mobile library innovations, positioning drones as a practical and sustainable solution for expanding library services in the 5IR era. It provides new perspectives on the logistical, social and environmental benefits of drone-enabled libraries, emphasizing their potential to enhance digital literacy, aid in disaster recovery and build stronger community connections.

AI Robustness Against Attacks in City-Scale Autonomous Drone Deployments

AI Robustness Against Attacks in City-Scale Autonomous Drone Deployments

Single- and Multi-Depot Optimization for UAV-Based IoT Data Collection in Neighborhoods

In this paper, we investigate the problem of deploying the minimum number of Unmanned Aerial Vehicles (UAVs) and determining their flying tours to collect data from all Internet of Things (IoT) sensors. We study this problem in a scenario with neighborhoods where a UAV can collect data from an IoT sensor if the distance between them is less than the wireless communication range of the IoT sensor. Since UAVs are powered by batteries with a limited amount of energy, we assume that the total energy consumed during the flying tour of each UAV is bounded by a given budget. We present the Minimum rooted drone Deployment Problem with Neighborhoods (MDPN), which is NP − hard , and propose two approximation algorithms for the single-depot case, where one of them is a bi-criteria approximation algorithm that returns a solution whose tour’s cost is violated by a factor of 1 + ϵ. Furthermore, we extend these two algorithms to the multi-depot scenario. Finally, we evaluate our algorithms in three different scenarios: the ideal one where the communication range is a circle and the data transfer rate is constant, and two more realistic scenarios where we introduce some degree of irregularity in the communication range and a non-constant rate in data transfer.

The Diverse Applications of Aerospace Drones: From Defense to Humanitarian and Commercial Uses

This research investigates the extensive applications of aerospace drones across defense, humanitarian, and commercial sectors, showcasing their transformative impact on modern industry. Aerospace drones have become pivotal tools in diverse settings—from defense and tactical operations to humanitarian aid and infrastructure management—offering operational efficiencies, cost savings, enhanced safety, and innovative solutions to complex challenges. This study explores defense applications such as military reconnaissance, where Vertical Take-Off and Landing (VTOL) drones enable effective surveillance in challenging terrains. In humanitarian settings, drones are utilized for disaster response in earthquake and flood zones, providing critical functions like search-and-rescue, real-time damage assessment, and medical supply delivery. Commercially, drones support long-range infrastructure inspections, smart agriculture, and environmental monitoring, driven by advancements in imaging and remote sensing. The project emphasizes the technical challenges and ethical considerations associated with drone deployment, particularly the need for robust AI and autonomous navigation systems in dynamic and unpredictable environments. Collaborations with international aerospace firms and humanitarian organizations have further refined drone integration strategies in both civilian and military contexts. The research concludes with a discussion on regulatory frameworks and environmental impacts, aiming to provide a comprehensive view of thefuture of aerospace drones and their role in addressing global challenges.

Agricultural Drones in Africa: Exploring Adoption, Applications, and Barriers

The adoption of drone technology in agriculture is transforming farming practices across Africa by enhancing resource efficiency, reducing operational costs, and promoting environmental sustainability. This paper explores the various applications of drones in African agriculture, including precision farming, crop monitoring, pest control, and livestock management. Drones enable farmers to optimize the use of water, fertilizers, and pesticides, leading to increased yields and improved profitability. Despite the potential benefits, the deployment of drones faces challenges such as high costs, lack of technical expertise, and regulatory barriers. This study highlights the importance of addressing these obstacles to facilitate the widespread adoption of drone technology among both small and large-scale farmers. By leveraging drones, African agriculture can improve food security, scale up operations, and contribute to the continent’s sustainable development goals. The findings of the review include case studies from Ghana, Kenya, and Nigeria which show that government intervention and private-sector partnerships are crucial for overcoming these barriers. This paper highlights the need for targeted training programs and policy reforms to enhance accessibility for smallholder farmers. By leveraging drones, African agriculture can improve food security, scale up operations, and contribute to the continent’s sustainable development goals.

Оценка влияния показателей эрозионного потенциала почвы по данным БПЛА на содержание гумуса в условиях опытного поля

The article is devoted to studying the possibilities of digital relief modeling based on UAV survey data when analyzing the spatial distribution of humus in the conditions of an experimental field. The scale of cartographic models was 1:2 000. A key site with an area of 2.62 ha, located within the boundaries of the educational and scientific experimental field of the Perm State Agricultural and Technological University on the territory of the Perm Municipal District of the Perm Territory, was selected as the object of research. The purpose of the study is to assess the spatial distribution of humus using UAV data based on indicators of soil erosion potential. The soil cover of the surveyed area is represented by soddy-podzolic soils of heavy granulometric composition. To obtain a digital terrain model using photogrammetry methods, UAV photography was carried out using a DJI mini 2 quadcopter. Photogrammetric image processing was performed in the Drone Deploy web application. The spatial distribution of humus content in the soils of the key area was determined at 45 points. Soil samples were taken from the depth of the arable layer (0–20 cm) and analyzed in the laboratory of the Department of Agrochemistry and Soil Science of the Perm State Agricultural and Technological University according to GOST 26213-84 with colorimetric finishing. On the territory of the experimental site under study, the humus content has a pronounced spatial autocorrelation. The map of humus content was constructed using the ordinary kriging method. When visually comparing the results of digital relief modeling with a map of the spatial distribution of humus in a key area, the dependence of the increase in the content of organic matter with the values of the elevation of the area, as well as with the distance to the thalwegs (removal zone), is clearly visible. To establish the influence of relief on the humus content in soils, a raster correlation was carried out in the SAGA program, which showed a close relationship between the humus content and the distance to the thalweg and the elevation of the area (r = 0.75). Indicators characterizing moisture content and surface curvature have little effect on the variation of humus content in space.

DRONES IN WARFARE: NIGERIA'S ADOPTION OF TECHNOLOGY IN FIGHTING INSECURITY

Rapid technological advancements have driven the increasing complexity of warfare, positioning unmanned aerial vehicles (UAVs), or drones, at the forefront of military operations globally. This study examines Nigeria's adoption of drone technology in its fight against insurgencies, banditry, and communal violence. As part of its evolving security strategy, Nigeria has integrated drones into its military operations to enhance intelligence gathering, surveillance, and precision strikes. Despite the operational benefits, the use of drones raises ethical concerns, especially related to civilian casualties, and poses challenges due to limited transparency and regulatory oversight. The study employed a systematic literature review (SLR), drawing on secondary data sources and reports that address the role, effectiveness, and challenges of drones in Nigeria's defense strategies. Key findings highlight that Nigeria's military, particularly the Air Force, has successfully deployed both indigenous and foreign-acquired drones, such as the Amebo, Gulma, and Chinese CH-4, to bolster its intelligence and combat operations. However, the lack of a robust legal framework and the need for improved training and data processing infrastructure hinder the full realization of drone technology's potential. Based on the findings, the study recommends enhancing Nigeria's regulatory framework to ensure ethical drone deployment, investing in indigenous UAV development, and improving inter-agency coordination for more efficient use of drone capabilities. These steps are crucial to ensuring that drones can effectively contribute to Nigeria's national security while minimizing the associated risks.

Fine-tuning GAN Models with Unpaired Aerial Images for RGB to NDVI Translation in Vegetation Index Estimation

Calculating the Normalized Difference Vegetation Index (NDVI) requires expensive multispectral cameras, posing challenges such as high costs and the need for technical expertise. This research aims to develop a method to transform RGB images obtained from Unmanned Aerial Vehicle (UAV) into NDVI images. Our proposed method leverages the CycleGAN model, an unsupervised image-to-image translation framework, to learn the intricate mapping between RGB values and NDVI. The model was trained on unpaired datasets of RGB and NDVI images, sourced from paddy fields located in Gresik and Yogyakarta, Indonesia. This process successfully encapsulated the complex correlation between these two modalities. Various training strategies were systematically investigated, including weight initialization schemes, fine-tuning procedures, and learning rate policies, to optimize the model's performance. The fine-tuned CycleGAN demonstrated superior performance in creating synthetic NDVI images from unpaired dataset, surpassing other methods in terms of fidelity, quality, and structural coherence. The results were impressive, with a Normalized Root Mean Square Error (NRMSE) of 0.327, a Peak Signal-to-Noise Ratio (PSNR) of 16.330, an Oriented FAST and Rotated BRIEF (ORB) score of 0.859, and a Structural Similarity Index (SSIM) of 0.757. The best performing CycleGAN model was then deployed on a low-spec microcomputer device, specifically the Raspberry Pi 4B with an average computation time of 21.0077 seconds. Raspberry Pi 4B was chosen for its lightweight, compact dimensions, and compatibility with efficient battery power connections, making it suitable for drone deployment.

Key features and applications of military drones: a case study from the Portuguese military ground forces

PurposeThe rapid advancement of new technologies necessitates the adaptation of existing resources to address the evolving demands of contemporary conflicts among nations. As exemplified by the emergence of Unmanned Aerial Systems (UAS) and Unmanned Aerial Vehicles (UAVs), these technologies have become indispensable components of military drone operations. This study investigates the role of innovation models in driving Portuguese Innovation and Development, focusing specifically on military drones.Design/methodology/approachThrough an examination of existing scientific and doctrinal literature, this research establishes a connection between theoretical concepts and the practical deployment of drones within the Portuguese ground forces. Employing a qualitative approach, this study follows a case study, with data collection following the principle of triangulation.FindingsThe findings of this research reveal several attributes crucial to drone utilization, such as optronic capability and drone range. These attributes are vital for ensuring high-quality, real-time imagery transmission and operational effectiveness in military activities.Originality/valueThis study contributes to the understanding of the implications of drone attributes for the Command, Control, Communications and Information Systems (C3IS) capabilities of the Portuguese ground forces. It highlights the importance of continued emphasis on drone development and innovation as a key priority for the Portuguese Army.

Conceptual Aspect of Measuring the Efficiency of Cargo Unmanned Aerial System

This article examines the conceptual framework for measuring the efficiency of unmanned systems, focusing on a task-oriented and problem-solving approach to evaluating the performance of cargo unmanned aerial vehicles. The efficiency of cargo unmanned aerial vehicles pertains to their ability to complete missions on time and cost-effectively, while maximizing utilization, minimizing resource loss, and maintaining an acceptable level of flight safety. It is important to highlight that the efficiency of cargo unmanned aerial vehicles is multifaceted, encompassing technical, operational, economic, environmental, and regulatory dimensions. Progress in each of these areas contributes to the successful deployment and optimization of cargo drones across various applications, from last-mile deliveries to supply chain operations in remote regions. The article presents two methodologies for assessing the efficiency of cargo drones.

Monitoring macroplastics in aquatic and terrestrial ecosystems: Expert survey reveals visual and drone-based census as most effective techniques

Anthropogenic litter, such as plastic, is investigated by the global scientific community from various fields employing diverse techniques. The goal is to assess and finally mitigate the pollutants' impacts on the natural environment. Plastic litter can accumulate in different matrices of aquatic and terrestrial ecosystems, impacting both biota and ecosystem functioning. Detection and quantification of macroplastics, and other litter, can be realized by jointly using visual census and remote sensing techniques. The primary objective of this research was to identify the most effective approach for monitoring macroplastic litter in riverine and marine environments through a comprehensive survey based on the experiences of the scientific community. Researchers involved in plastic pollution evaluated four litter occurrence and flux investigation methods (visual census, drone-based surveys, satellite imagery, and GPS/GNSS trackers) through a questionnaire. Traditional visual census and drone deployment were deemed as the most popular approaches among the 46 surveyed researchers, while satellite imagery and GPS/GNSS trackers received lower scores due to limited field validation and short performance ranges, respectively. On a scale from 0 to 5, visual census and drone-based surveys obtained 3.5 and 2.0, respectively, whereas satellite imagery and alternative solutions received scores lower than 1.2. Visual and drone censuses were used in high, medium and low-income countries, while satellite census and GPS/GNSS trackers were mostly used in high-income countries. This work provides an overview of the advantages and drawbacks of litter investigation techniques, contributing i) to the global harmonization of macroplastic litter monitoring and ii) providing a starting point for researchers and water managers approaching this topic. This work supports the selection and design of reliable and cost-effective monitoring approaches to mitigate the ambiguity in macroplastic data collection, contributing to the global harmonization of macroplastic litter monitoring protocols.

Optimising Drone-Assisted Logistics for Urban Last-Mile Delivery: An Overview of Applications, Methodologies, and Emerging Trends

The rapid evolution of drone-assisted logistics for urban last-mile (ULM) delivery has garnered significant interest from both academia and industry. This article presents a comprehensive review of the state-of-the-art research and practical implementations of ULM systems, focusing on the use of unmanned aerial vehicles (UAVs) for the final stage of goods and parcel delivery in urban environments. The applicability of UAV-based logistics across various contexts, including urban and rural areas, is examined, with real-world case studies highlighted to demonstrate practical uses. Key methodologies and models employed in optimising UAV routing and operations are discussed, particularly those that enhance the efficiency and reliability of ULM. The critical advantages and limitations of drone-assisted last-mile logistics are analysed, providing insights into the operational, regulatory, and technological challenges. The discussion is further expanded by addressing emerging trends in UAV technology, as well as innovations in drone deployment strategies and the evolving regulatory landscape. In conclusion, potential theoretical advancements and future applications of ULM systems are outlined, with an emphasis on integrating drones into broader logistics networks and smart city frameworks. The insights offered aim to guide future research and practical developments in this rapidly advancing field.

Synchronising an IMX219 image sensor and AS7265x spectral sensor to make a novel low-cost spectral camera

A low-cost novel spectral camera able to be used for near infrared spectroscopy was made by using a Jetson Nano to synchronize a Sony IMX219 NOIR autofocus image sensor, an AMS AS7265x 18-channel spectral sensor and Osram SFH 4737 broadband infrared LED’s. Synchronizing an image sensor and spectral sensor augments a standard RGB image with light spectrum information; capturing the light distribution information normally lost in RGB image capture. Sutherland et al. [1] used this novel spectral camera to examine the dorsal surface of juvenile lobsters as a possible pre-moult detector. Having the image and spectrum in combination allowed the incomplete and unmineralized post-moult dorsal surface to be characterized with 86.7% accuracy for the first time. A proposed application for the spectral camera is to omit the local SFH 4737 light source and use the camera in daylight, effectively making a low-cost substitute hyperspectral snapshot camera. In this configuration the camera may have application for low-cost drone deployment for small scale agriculture.

Optimal drone deployment for cost‐effective and sustainable last‐mile delivery operations

AbstractDelivery by drones holds significant potential to solve issues (such as high costs, access to remote areas, etc.) faced in last‐mile delivery operations, particularly in the e‐commerce industry. Still, it involves complex issues such as multi‐trip operations, energy estimation, and battery recharge planning. A sound drone delivery problem entails an optimal drone deployment plan with routing details at the lowest possible cost. To this end, this study focuses on formulating a delivery problem that involves multi‐trip drone routing, energy optimization, and travel time optimization problems where energy consumption by drones is modeled as a non‐linear function. We develop a mixed integer non‐linear programming model as an integrated optimization model. This model aims to: (a) maximize revenue by meeting demand completely without leaving idle drones, (b) optimize energy use by drones, and (c) minimize the required drone fleet size for an optimal plan. The proposed model is solved using the Gurobi Solver, which employs data supplied by a well‐known e‐commerce firm. We introduce a two‐phase heuristic solution methodology to tackle larger networks’ complexities. This method consists of the clustering phase (K‐means clustering method) and the optimization phase. The robustness of the developed mathematical modeling is demonstrated by testing with varied large problem instances. The evaluation shows that expanding destination options boosts drone demand until saturation, necessitating more drones. Efficient route planning and fleet adjustments are crucial for meeting rising demand and satisfying customers amidst dense clustering. This model helps e‐commerce manage daily last‐mile drone deliveries and anticipate future growth.

An Empirical Study of Factors Influencing Drone Terrorist Attack Casualties

Recognizing the pivotal role of casualties as a metric for assessing the success of terrorist acts, this study endeavors to unravel the underlying factors shaping the casualty count in drone terrorist attacks across the globe. By applying Zero Negative Binomial Regression Analysis on data sourced from the Global Terrorism Database, we discern significant factors influencing the number of terrorist casualties. Our findings reveal the paramount importance of the target facility's significance, the attack type, the utilization of remote-controlled drones, the deployment of suicide drones equipped with explosive payloads, and the audacious strategy of swarming drone attacks.

Intelligent obstacle avoidance algorithm for safe urban monitoring with autonomous mobile drones

The growing field of urban monitoring has increasingly recognized the potential of utilizing autonomous technologies, particularly in drone swarms. The deployment of intelligent drone swarms offers promising solutions for enhancing the efficiency and scope of urban condition assessments. In this context, this paper introduces an innovative algorithm designed to navigate a swarm of drones through urban landscapes for monitoring tasks. The primary challenge addressed by the algorithm is coordinating drone movements from one location to another while circumventing obstacles, such as buildings. The algorithm incorporates three key components to optimize the obstacle detection, navigation, and energy efficiency within a drone swarm. Firstly, the algorithm utilizes a method for calculating the position of a virtual leader, acting as a navigational beacon to influence the overall direction of the swarm. Secondly, the algorithm identifies observers within the swarm based on the current orientation. To further refine obstacle avoidance, the third component involves the calculation of angular velocity using fuzzy logic. This approach considers the proximity of detected obstacles through operational rangefinders and the target’s location, allowing for a nuanced and adaptable computation of angular velocity. The integration of fuzzy logic enables the drone swarm to adapt to diverse urban conditions dynamically, ensuring practical obstacle avoidance. The proposed algorithm demonstrates enhanced performance in the obstacle detection and navigation accuracy through comprehensive simulations. The results suggest that the intelligent obstacle avoidance algorithm holds promise for the safe and efficient deployment of autonomous mobile drones in urban monitoring applications.

On-demand high-resolution areal scouting via unmanned aerial vehicles enables sustainable near-surface geoscience data acquisition

An accurate data acquisition plan is critical for near-surface geoscience investigations. Detailed understanding of the terrain and land cover of the survey area is essential to designing a data acquisition layout that efficiently meets the objective while mapping potential obstacles. Using satellite-based data is the most affordable and straightforward method to obtain this information. However, near-surface geoscience investigations demand a higher-resolution map than commonly available satellite imagery to design a detailed acquisition plan. This paper presents a concept that utilizes unmanned aerial vehicles (UAVs) to successfully and sustainably perform on-demand high-resolution areal scouting to aid near-surface geoscience data acquisition campaigns and seismic drone deployment. We share the results of two field trial cases where the presented concept was evaluated. Case A is a 16 km2 extensive outcrop investigation in an arid desert environment. The initial satellite-based acquisition plan was changed considerably when UAV data sets became available. This led to an approximately 60% improvement in data productivity and efficiency, effectively reducing the carbon footprint of conventional scouting operations. Case B utilizes high-resolution areal scouting to determine the safe landing zone for autonomous seismic drone swarms to further support sustainable geophysical data acquisition. The UAV data enable seismic drone swarms to land optimally on preprogrammed landing points while navigating subsatellite-resolution obstacles. These two successful cases suggest that analogous productivity and efficiency improvements may be achieved in industrial-scale land seismic data acquisition planning that utilizes the UAV data set.