Unmanned Aerial Vehicles for Wildland Fires: Sensing, Perception, Cooperation and Assistance

On designing a configurable UAV autopilot for unmanned quadrotors

Unmanned Aerial Vehicles (UAVs) and quadrotors are being used in an increasing number of applications. The detection and management of forest fires is continually improved by the incorporation of new economical technologies in order to prevent ecological degradation and disasters. Using an inner-outer loop design, this paper discusses an attitude and altitude controller for a quadrotor. As a highly nonlinear system, quadrotor dynamics can be simplified by assuming several assumptions. Quadrotor autopilot is developed using nonlinear feedback linearization technique, LQR, SMC, PD, and PID controllers. Often, these approaches are used to improve control and to reject disturbances. PD-PID controllers are also deployed in the tracking and surveillance of smoke or fire by intelligent algorithms. In this paper, the efficiency using a combined PD-PID controllers with adjustable parameters have been studied. The performance was assessed by simulation using matlab Simulink. The computational study conducted to assess the proposed approach showed that the PD-PID combination presented in this paper yields promising outcomes.

Enhancing the Localization Accuracy of UAV Images under GNSS Denial Conditions

Unmanned aerial vehicles (UAVs) are widely used in many industries. The use of UAV images for surveying requires that the images contain high-precision localization information. However, the accuracy of UAV localization can be compromised in complex GNSS environments. To address this challenge, this study proposed a scheme to improve the localization accuracy of UAV sequences. The combination of traditional and deep learning methods can achieve rapid improvement of UAV image localization accuracy. Initially, individual UAV images with high similarity were selected using an image retrieval and localization method based on cosine similarity. Further, based on the relationships among UAV sequence images, short strip sequence images were selected to facilitate approximate location retrieval. Subsequently, a deep learning image registration network, combining SuperPoint and SuperGlue, was employed for high-precision feature point extraction and matching. The RANSAC algorithm was applied to eliminate mismatched points. In this way, the localization accuracy of UAV images was improved. Experimental results demonstrate that the mean errors of this approach were all within 2 pixels. Specifically, when using a satellite reference image with a resolution of 0.30 m/pixel, the mean error of the UAV ground localization method reduced to 0.356 m.

Cooperative Positioning Method of a Multi-UAV Based on an Adaptive Fault-Tolerant Federated Filter

Aiming at the problem of the low cooperative positioning accuracy and robustness of multi-UAV formation, a cooperative positioning method of a multi-UAV based on an adaptive fault-tolerant federated filter is proposed. Combined with the position of the follower UAV and leader UAV, and the relative range between them, a cooperative positioning model of the follower UAV is established. On this basis, an adaptive fault-tolerant federated filter is designed. Fault detection and isolation technology are added to improve the positioning accuracy of the follower UAV and the fault tolerance performance of the filter. Meanwhile, the measurement noise matrix is adjusted by the adaptive information allocation coefficient to reduce the impact of undetected fault information on the sub-filter and global estimation accuracy. The simulation results show that the adaptive fault-tolerant federated algorithm can greatly improve the positioning accuracy, which is 83.4% higher than that of the absolute positioning accuracy of a single UAV. In the case of a gradual fault, the method has a stronger fault-tolerant performance and reconstruction performance.

Bio-Inspired Optimization-Based Path Planning Algorithms in Unmanned Aerial Vehicles: A Survey

Advancements in electronics and software have enabled the rapid development of unmanned aerial vehicles (UAVs) and UAV-assisted applications. Although the mobility of UAVs allows for flexible deployment of networks, it introduces challenges regarding throughput, delay, cost, and energy. Therefore, path planning is an important aspect of UAV communications. Bio-inspired algorithms rely on the inspiration and principles of the biological evolution of nature to achieve robust survival techniques. However, the issues have many nonlinear constraints, which pose a number of problems such as time restrictions and high dimensionality. Recent trends tend to employ bio-inspired optimization algorithms, which are a potential method for handling difficult optimization problems, to address the issues associated with standard optimization algorithms. Focusing on these points, we investigate various bio-inspired algorithms for UAV path planning over the past decade. To the best of our knowledge, no survey on existing bio-inspired algorithms for UAV path planning has been reported in the literature. In this study, we investigate the prevailing bio-inspired algorithms extensively from the perspective of key features, working principles, advantages, and limitations. Subsequently, path planning algorithms are compared with each other in terms of their major features, characteristics, and performance factors. Furthermore, the challenges and future research trends in UAV path planning are summarized and discussed.

A Wildfire Smoke Detection System Using Unmanned Aerial Vehicle Images Based on the Optimized YOLOv5

Wildfire is one of the most significant dangers and the most serious natural catastrophe, endangering forest resources, animal life, and the human economy. Recent years have witnessed a rise in wildfire incidents. The two main factors are persistent human interference with the natural environment and global warming. Early detection of fire ignition from initial smoke can help firefighters react to such blazes before they become difficult to handle. Previous deep-learning approaches for wildfire smoke detection have been hampered by small or untrustworthy datasets, making it challenging to extrapolate the performances to real-world scenarios. In this study, we propose an early wildfire smoke detection system using unmanned aerial vehicle (UAV) images based on an improved YOLOv5. First, we curated a 6000-wildfire image dataset using existing UAV images. Second, we optimized the anchor box clustering using the K-mean++ technique to reduce classification errors. Then, we improved the network's backbone using a spatial pyramid pooling fast-plus layer to concentrate small-sized wildfire smoke regions. Third, a bidirectional feature pyramid network was applied to obtain a more accessible and faster multi-scale feature fusion. Finally, network pruning and transfer learning approaches were implemented to refine the network architecture and detection speed, and correctly identify small-scale wildfire smoke areas. The experimental results proved that the proposed method achieved an average precision of 73.6% and outperformed other one- and two-stage object detectors on a custom image dataset.

Distributed Blockchain-Based Platform for Unmanned Aerial Vehicles

Internet of Things (IoT)-inspired drone environment is having a greater influence on daily lives in the form of drone-based smart electricity monitoring, traffic routing, and personal healthcare. However, communication between drones and ground control systems must be protected to avoid potential vulnerabilities and improve coordination among scattered UAVs in the IoT context. In the current paper, a distributed UAV scheme is proposed that uses blockchain technology and a network topology similar to the IoT and cloud server to secure communications during data collection and transmission and reduce the likelihood of attack by maliciously manipulated UAVs. As an alternative to relying on a traditional blockchain approach, a unique, safe, and lightweight blockchain architecture is proposed that reduces computing and storage requirements while keeping privacy and security advantages. In addition, a unique reputation-based consensus protocol is built to assure the dependability of the decentralized network. Numerous types of transactions are established to characterize diverse data access. To validate the presented blockchain-based distributed system, performance evaluations are conducted to estimate the statistical effectiveness in the form of temporal delay, packet flow efficacy, precision, specificity, sensitivity, and security efficiency.

LLAM-MDCNet for Detecting Remote Sensing Images of Dead Tree Clusters

Clusters of dead trees are forest fires-prone. To maintain ecological balance and realize its protection, timely detection of dead trees in forest remote sensing images using existing computer vision methods is of great significance. Remote sensing images captured by Unmanned aerial vehicles (UAVs) typically have several issues, e.g., mixed distribution of adjacent but different tree classes, interference of redundant information, and high differences in scales of dead tree clusters, making the detection of dead tree clusters much more challenging. Therefore, based on the Multipath dense composite network (MDCN), an object detection method called LLAM-MDCNet is proposed in this paper. First, a feature extraction network called Multipath dense composite network is designed. The network’s multipath structure can substantially increase the extraction of underlying and semantic features to enhance its extraction capability for rich-information regions. Following that, in the row, column, and diagonal directions, the Longitude Latitude Attention Mechanism (LLAM) is presented and incorporated into the feature extraction network. The multi-directional LLAM facilitates the suppression of irrelevant and redundant information and improves the representation of high-level semantic feature information. Lastly, an AugFPN is employed for down-sampling, yielding a more comprehensive representation of image features with the combination of low-level texture features and high-level semantic information. Consequently, the network’s detection effect for dead tree cluster targets with high-scale differences is improved. Furthermore, we make the collected high-quality aerial dead tree cluster dataset containing 19,517 images shot by drones publicly available for other researchers to improve the work in this paper. Our proposed method achieved 87.25% mAP with an FPS of 66 on our dataset, demonstrating the effectiveness of the LLAM-MDCNet for detecting dead tree cluster targets in forest remote sensing images.

The Use of Swarms of Unmanned Aerial Vehicles in Mitigating Area Coverage Challenges of Forest-Fire-Extinguishing Activities: A Systematic Literature Review

The use of Unmanned Aerial Vehicles (UAVs), colloquially known as drones, has grown rapidly over the past two decades and continues to expand at a rapid pace. This has resulted in the production of many research papers addressing the use of UAVs in a variety of applications, such as forest firefighting. The main purpose of this paper is to provide a comprehensive overview of UAV-based forest-fire-extinguishing activity (FFEA) operations. To achieve this goal, a systematic literature review was conducted to answer a specific set of questions, which were carefully formulated to address the results of research conducted between 2008 and 2021. This study aims to (i) expand our understanding of the development of UAVs and their current contributions to the FFEA; (ii) identify particularly novel or unique applications and characteristics of UAV-based fire-extinguishing systems; (iii) provide guidance for exploring and revising further ideas in this field by identifying under-researched topics and other areas in which more contributions are needed; and (iv) explore the feasibility of using UAV swarms to enable autonomous firefighting in the forest without human intervention. Of the 1353 articles systematically searched across five databases (Google Scholar, ACM Digital Library, Science Direct, Scopus, and IEEE Explore), 51 highly relevant articles were found to meet the inclusion criteria; therefore, they were analyzed and discussed. The results identified several gaps in this field of study among them the complexity of coordination in multi-robotic systems, the lack of evaluation and implementation of fire extinguishing systems, the inability of handling multiple spot fires, and poor management of time and resources. Finally, based on the conducted review, this paper provides significant research directions that require further investigations by researchers in this field including, the deployment of UAV-based Swarm Robotics, further study on the characteristics of the fire extinguishing systems; design more effective area coverage; and the propose of a self-firefighting model that enables individuals to decide on the course of events efficiently and locally for better utilization and management of time and resources.

WILD HOPPER: A Heavy-Duty UAV for Day and Night Firefighting Operations

Forest fires are among the most dangerous accidents, as they lead to the repercussions of climate change by reducing oxygen levels and increasing carbon dioxide levels. These risks led to the attention of many institutions worldwide, most notably the European Union and the European Parliament, which led to the emergence of many directives and regulations aimed at controlling the phenomenon of forest fires in Europe, such as the (E.U.) 2019/570. Among the proposed solutions, the usage of unmanned aerial vehicles (UAVs) is considered to operate alongside existing aircraft and helicopters through extinguishing forest fires. Scientific researches in this regard have shown the high effectiveness use of UAVs. Still, some defects and shortcomings appeared during practical experiments represented in the limited operating time and low payload. As UAVs are used for firefighting forest fires, they must be characterized by the heavy payload for the extinguishing fluids, long time for flight endurance during the mission, the ability to high maneuver, and work as a decision-making system.

In this paper, a new UAV platform for forest firefighting is represented named WILD HOPPER.

WILD HOPPER is a 600-liter platform designed for forest firefighting. This payload capacity overcomes typical limitations of electrically powered drones that cannot be used for anything more than fire monitoring, as they do not have sufficient lifting power. The enhanced capabilities of the WILD HOPPER allow it to complement existing aerial means and overcome their main limitations, especially the need to cover night operations. This allows reducing the duration of the wildfires heavily by allowing continuous aerial support to the extinguishing activities once the conventional aerial means (hydroplanes and helicopters) are set back to the base at night. On the other hand, WILD HOPPER has significant powerful advantages due to the accuracy of the release, derived from multirotor platform dynamic capabilities.

Novel Drone Design Using an Optimization Software with 3D Model, Simulation, and Fabrication in Drone Systems Research

This paper presents the design of a small size Unmanned Aerial Vehicle (UAV) using the 3DEXPERIENCE software. The process of designing the frame parts involves many methods to ensure the parts can meet the requirements while conforming to safety and industry standards. The design steps start with the selection of materials that can be used for the drone, which are polylactic acid (PLA), acrylonitrile styrene acrylate (ASA), and acrylonitrile butadiene styrene (ABS). The drone frame consists of four main parts, which are the center top cover (50 g), the side top cover (10 g), the middle cover (30 g), and the drone’s arm (80 g). A simulation was carried out to determine the stress, displacement, and weight of the drone’s parts. Additionally, a trade-off study was conducted to finalize the shapes of the parts and the various inputs based on their priorities. The outcome of this new design can be represented in design concepts, which involve the use of the snap hook function to assemble two body parts together, namely the middle cover and the center top cover, without the need of an additional fastener.

Deep Learning and Transformer Approaches for UAV-Based Wildfire Detection and Segmentation

Wildfires are a worldwide natural disaster causing important economic damages and loss of lives. Experts predict that wildfires will increase in the coming years mainly due to climate change. Early detection and prediction of fire spread can help reduce affected areas and improve firefighting. Numerous systems were developed to detect fire. Recently, Unmanned Aerial Vehicles were employed to tackle this problem due to their high flexibility, their low-cost, and their ability to cover wide areas during the day or night. However, they are still limited by challenging problems such as small fire size, background complexity, and image degradation. To deal with the aforementioned limitations, we adapted and optimized Deep Learning methods to detect wildfire at an early stage. A novel deep ensemble learning method, which combines EfficientNet-B5 and DenseNet-201 models, is proposed to identify and classify wildfire using aerial images. In addition, two vision transformers (TransUNet and TransFire) and a deep convolutional model (EfficientSeg) were employed to segment wildfire regions and determine the precise fire regions. The obtained results are promising and show the efficiency of using Deep Learning and vision transformers for wildfire classification and segmentation. The proposed model for wildfire classification obtained an accuracy of 85.12% and outperformed many state-of-the-art works. It proved its ability in classifying wildfire even small fire areas. The best semantic segmentation models achieved an F1-score of 99.9% for TransUNet architecture and 99.82% for TransFire architecture superior to recent published models. More specifically, we demonstrated the ability of these models to extract the finer details of wildfire using aerial images. They can further overcome current model limitations, such as background complexity and small wildfire areas.

Toward Integrated Large-Scale Environmental Monitoring Using WSN/UAV/Crowdsensing: A Review of Applications, Signal Processing, and Future Perspectives

Fighting Earth's degradation and safeguarding the environment are subjects of topical interest and sources of hot debate in today's society. According to the United Nations, there is a compelling need to take immediate actions worldwide and to implement large-scale monitoring policies aimed at counteracting the unprecedented levels of air, land, and water pollution. This requires going beyond the legacy technologies currently employed by government authorities and adopting more advanced systems that guarantee a continuous and pervasive monitoring of the environment in all its different aspects. In this paper, we take the research on integrated and large-scale environmental monitoring a step further by providing a comprehensive review that covers transversally all the main applications of wireless sensor networks (WSNs), unmanned aerial vehicles (UAVs), and crowdsensing monitoring technologies. By outlining the available solutions and current limitations, we identify in the cooperation among terrestrial (WSN/crowdsensing) and aerial (UAVs) sensing, coupled with the adoption of advanced signal processing techniques, the major pillars at the basis of future integrated (air, land, and water) and large-scale environmental monitoring systems. This review not only consolidates the progresses achieved in the field of environmental monitoring, but also sheds new lights on potential future research directions and synergies among different research areas.