Nexus of technologies leads to a digital revolution to reshape the construction industry, such as artificial intelligence of things (AIoT), but the leverage through integration with drones is still unexplored. The study conducts a systematic literature review of relevant literature retrieved from the Scopus and Web of Science repositories to uncover the applications of AIoT-enabled drones in the construction industry. Preferred reporting items for systematic and meta-analyses protocols were applied to conduct a review of 182 retrieved articles. The publication trend peaked in 2023, with dips in 2020 and 2024. IEEE journal supersedes other publishers. Most research was conducted in India, followed by the USA and China. The most recurring keywords for this review were ‘Internet of Things’ and ‘Artificial Intelligence,’ based on the Scopus database. Keyword co-occurrence revealed four knowledge clusters. Seven areas of application are identified for AIoT-powered drones in the construction sector. A detailed discourse is conducted on the findings to unveil their implications for theory and practice. Challenges to adopting AIoT-powered drones are explored, and future directions for research and industry are delineated. The study aims to accelerate the adoption of AIoT technology in the construction industry. Researchers, academics, and industry practitioners are the target of this study as it seeks to expedite the adoption of AIoT in the construction industry, owing to its promising implications.

With the rapid advancement of unmanned aerial vehicle (UAV) technologies, drone swarms have been increasingly adopted in applications ranging from agriculture and logistics to defense and performance arts. However, conventional swarm control architectures, predominantly centralized, remain limited in scalability, adaptability, and robustness under dynamic conditions. To address these limitations, this study presents a bio-inspired formation control framework that integrates decentralized coordination and autonomous role assignment. The proposed system incorporates a reference–follower mechanism, enabling drones to dynamically select reference units based on spatial proximity, thereby enhancing inter-drone interaction and formation stability. Furthermore, a hybrid communication architecture based on Robot Operating System (ROS) and Message Queuing Telemetry Transport (MQTT) protocols is developed to overcome the constraints of traditional ROS communication frameworks and improve scalability. Finally, simulation and real-world flight experiments validate the proposed approach, demonstrating significant improvements in formation flexibility, communication efficiency, and adaptive leader switching compared to conventional leader–follower and virtual structure models.

Unmanned aerial vehicles, or drones, have become a weapon of choice on the modern battlefield. As military and civilian industries try to develop effective counter-drone systems, early detection of flying drones still poses multiple challenges to state-of-the-art computer vision technologies. These challenges include a growing variety of military and commercial drones, their small size compared to piloted aircraft, blending with the background, similarity to birds, etc. In our experiments on drone images of variable size, we have observed a rapid drop in the accuracy of a state-of-the-art drone detection model when applied to distant drones that take a relatively small area on the entire image. However, we show that this early detection accuracy can be significantly improved by applying the drone detection model to an image masked by the Canny edge detector. We suggest applying the model to the original and the masked images in parallel and determining a drone detection decision by the highest confidence value under the condition that the detected object is not recognized as a bird by a general-purpose object detection model. The results of our evaluation experiments confirm the effectiveness of the proposed drone detection approach.

The safe integration of new and emerging technologies such as remotely piloted aircraft (RPA) into existing airspace will require pilots’ acceptance of such technology. Therefore, the main aim of the present research is to understand pilots’ willingness to operate with crewed and uncrewed aircraft in an integrated airspace. The research also aims to examine whether factors such as vertical separation, automation levels, and technology acceptance affect pilots’ level of airspace integration acceptance. Eighty-five pilots completed a battery of surveys, comprising a demographics questionnaire, a technology acceptance questionnaire, as well as a newly created Aircraft Separation Questionnaire. The results revealed a clear automation acceptance threshold in acceptance between automation levels 3 and 4, the point at which decision-making transitioned from the human to the automation. The analysis found no significant relationship between vertical separation and technology acceptance. These results illustrate that pilots are more receptive towards integrated airspace operations when controlling decisions are undertaken by a human.

The flight environment of unmanned aerial vehicles faces various challenges. To effectively navigate and perform tasks, they need to effectively integrate multiple sensors. This study applies the adaptive weighted average method, combined with data from global positioning system, inertial measurement unit, three-dimensional optical detection and ranging, and uses linear Kalman filtering to smooth the merged velocity data. High-order B-spline curves for route planning and applying flight constraint formulas to better adapt are used to the dynamics of unmanned aerial vehicles. The research results indicated that the improved adaptive weighting algorithm had high comprehensive performance for multi-sensor data fusion, with the highest accuracy, robustness, real-time performance, and consistency of 94.2%, 93.7%, 100%, and 95.6%, respectively. The flight path lengths planned by the A* algorithm and higher-order B-spline curve were 15.7 and 16.3 m, respectively, and the flight time was 8.2 and 7.1 s, respectively. The flight path planned by higher-order B-spline curve was further away from obstacles. The use of adaptive weighted fusion and linear Kalman filtering facilitates the fusion of multi-sensor data, and autonomous flight routes planned using high-order B-spline curves can also meet the needs of unmanned aerial vehicle flight in complex flight environments.

In the path planning of UAVs, autonomous decision-making and control are challenging tasks in the uncertain 3D environment consisting of static and dynamic obstacles. Hence, the selection of appropriate path-planning approaches is essential. In the proposed work, we have considered the meta-heuristic approaches only for an in-depth review. Metaheuristic approaches have been remarkably known for solving complex problems, optimal solutions, and lesser computational complexity compared to deterministic approaches that produce an inefficient solution. An in-depth review has been made by considering the approaches used for path planning, their advantages, disadvantages, applications, the type of time domain (offline or online), type of environment (simulation or real time), hybridization with other approaches, single or multiple UAV system, and obstacle handled (static or dynamic). It is observed that current meta-heuristic methods face constraints like inadequate convergence rates, entrapment in local optima, and complex operations, necessitating continuous development of novel approaches. Implementation of path-planning approaches are very much limited to simulation study over experimental analysis. Hybrid algorithms emerge as a potential solution for tackling these hurdles and optimizing UAV navigation, particularly in dynamic environments involving multiple UAVs. The paper highlights key research gaps, trends, along with prospects in the field of research.

This paper underscores the significance of safety and reliability in the realm of unmanned aerial vehicle (UAV) technologies, and how regulations play a pivotal role in ensuring their responsible use. We have analyzed safety incidents and trends both in Canada and globally, noting a decline in incidents attributed to enhanced regulations. Our comparative analysis of different UAV technologies identified batteries as the most reliable power supply, Global Navigation Satellite System as the most effective navigation system, and light detection and ranging as the optimal optical sensor due to regulatory compliance and system redundancies. We also examined the regulatory framework in Canada, comparing it with the risk-based approach of the European Union Aviation Safety Agency and the efforts of Joint Authorities for Rule-making on Unmanned Systems towards global harmonization. Furthermore, we highlighted emerging trends in automation and flight control technologies, with a focus on European regulations shaping UAV automation trends. In conclusion, by adhering to best practices from other regulatory bodies, embracing emerging trends, and adopting a risk-based approach, Canada can promote the growth of the UAV industry while ensuring safety and reliability in UAV technologies.

While biometric recognition typically uses features such as face, fingerprint, and iris to identify individuals, this study focuses on utilising specific characteristics to identify gender. The aim of this article is to propose a procedure for gender recognition under specific conditions. The specific condition addressed is outdoor area monitoring, which presents challenges such as varying lighting conditions and limited camera placement options. To tackle this, a proposed procedure utilises thermal images captured by the drone equipped with a thermal camera. The advantage of thermal images is their independence from ambient light conditions. The captured images are resized and processed using convolutional neural networks (CNNs) (AlexNet, VGG-16, VGG-19) for feature extraction and binary classification. A freely available database of thermal face images is used for training the CNNs, while a own created dataset of thermal images obtained by the drone is used for testing. The findings indicate that the optimised CNNs achieve classification accuracies of 82.4% (VGG-16), 82.9% (AlexNet), and 85.5% (VGG-19). The original contribution of this study lies in demonstrating the suitability of face thermal images obtained through drones for gender recognition purposes.

Autonomous blimps have potential applications in surveillance, monitoring, and advertising. Due to their lower payload capacities and possible unstable flight profile, small blimps have been mostly used in indoor applications. However, recent advancements in their design and control have increased the prospects of deploying them for outdoor applications. This study presents a literature review of various aspects that encompass the unique elements of blimps’ design and operations followed by a discussion on the modern applications. The review focuses on advancements made in the fundamental attributes of blimps, including design, propulsion, navigation, and control. The review reveals that recent successes in using blimps for various missions, where heavier-than-air platforms have been usually used, highlight the potential for blimps to offer a lightweight and low-risk alternative. The relatively stable operation of blimps in low winds and longer-duration hovering capability can make them a preferred platform for rescue, source localization, and space applications. However, their stability in extreme environments is a challenge, in addition to their lower mobility and problems in accurately predicting control parameters. Thus, this review concludes with an overview of blimps’ futuristic applications of miniature blimps and recommendations to address the challenges in using them in real-world missions.

Drone-based multispectral sensing is a valuable tool for dryland spatial ecology, yet there has been limited investigation of the reproducibility of measurements from drone-mounted multispectral camera array systems or the intercomparison between drone-derived measurements, field spectroscopy, and satellite data. Using radiometrically calibrated data from two multispectral drone sensors (MicaSense RedEdge (MRE) and Parrot Sequoia (PS)) co-located with a transect of hyperspectral measurements (tramway) in the Chihuahuan desert (New Mexico, USA), we found a high degree of correspondence within individual drone data sets, but that reflectance measurements and vegetation indices varied between field, drone, and satellite sensors. In comparison to field spectra, MRE had a negative bias, while PS had a positive bias. In comparison to Sentinel-2, PS showed the best agreement, while MRE had a negative bias for all bands. A variogram analysis of NDVI showed that ecological pattern information was lost at grains coarser than 1.8 m, indicating that drone-based multispectral sensors provide information at an appropriate spatial grain to capture the heterogeneity and spectral variability of this dryland ecosystem in a dry season state. Investigators using similar workflows should understand the need to account for biases between sensors. Modelling spatial and spectral upscaling between drone and satellite data remains an important research priority.