Unmanned Aerial Vehicle Navigation Research Articles

A Novel Geo-Localization Method for UAV and Satellite Images Using Cross-View Consistent Attention

Geo-localization has been widely applied as an important technique to get the longitude and latitude for unmanned aerial vehicle (UAV) navigation in outdoor flight. Due to the possible interference and blocking of GPS signals, the method based on image retrieval, which is less likely to be interfered with, has received extensive attention in recent years. The geo-localization of UAVs and satellites can be achieved by querying pre-obtained satellite images with GPS-tagged and drone images from different perspectives. In this paper, an image transformation technique is used to extract cross-view geo-localization information from UAVs and satellites. A single-stage training method in UAV and satellite geo-localization is first proposed, which simultaneously realizes cross-view feature extraction and image retrieval, and achieves higher accuracy than existing multi-stage training techniques. A novel piecewise soft-margin triplet loss function is designed to avoid model parameters being trapped in suboptimal sets caused by the lack of constraint on positive and negative samples. The results illustrate that the proposed loss function enhances image retrieval accuracy and realizes a better convergence. Moreover, a data augmentation method for satellite images is proposed to overcome the disproportionate numbers of image samples. On the benchmark University-1652, the proposed method achieves the state-of-the-art result with a 6.67% improvement in recall rate (R@1) and 6.13% in average precision (AP). All codes will be publicized to promote reproducibility.

Machine learning and UAV path following identification algorithm based on navigation spoofing

With advances in navigation technology, unmanned aerial vehicles (UAVs) have become widely available to all sections of society. Given the potential hazards of UAVs, as seen from their use in the Russia–Ukraine war and security incidents at London and Baghdad airports, counter-UAV technology is receiving unprecedented attention. This paper describes a method for taking control of a UAV indirectly by navigation spoofing and luring it to a designated area from which it can be neutralized. Our contributions are threefold: first, we analyze the limitations of the traditional state estimation and control model for UAV navigation based on the integration of the Global Navigation Satellite System and Inertial Navigation System. Second, we propose a particle hypothesis and planning model that is insensitive to the particular UAV navigation system, and decompose the UAV navigation spoofing process into two steps: identification and planning. Finally, to overcome the poor heading angle prediction accuracy of unary polynomial regression, we propose a support vector regression algorithm that improves the prediction accuracy from 1.5° to 1.01° under navigation spoofing. Experimental results using the proposed navigation spoofing method prove that machine learning offers significant advantages in modeless identification.

A robust multiple Unmanned Aerial Vehicles 3D path planning strategy via improved particle swarm optimization

Path planning algorithms for Unmanned Aerial Vehicles (UAVs) are essential in various domains, such as search and rescue operations, agriculture, and delivery services. Nonetheless, finding optimal flight paths in complex environments with obstacles remains challenging. This paper proposes a novel path planning algorithm that uses a Nash equilibrium approach based on game theory to strike a balance between the exploitation and exploration capabilities of UAVs. The algorithm is designed in a simulated flight environment with obstacles, utilizing the self-awareness and group awareness coefficients from particle swarm optimization(PSO) as participants in the game theory model. The proposed path planning algorithm significantly improves the navigation of multiple UAVs in complex scenarios with obstacles by achieving a balance between their exploitation and exploration capabilities. Simulation experiments demonstrate that the proposed method surpasses traditional approaches, exhibiting an average improvement of 32.57%, 32.17%, and 29.33% in the algorithm convergence time, average flight distance, and average flight time, respectively. The significance of this research lies in its contribution to advancing UAV path planning algorithms. By integrating game theory and PSO, the proposed method optimizes the exploration and exploitation capabilities of UAVs, leading to improved navigation and resource utilization.

Collision-Free 3-D Navigation of a UAV Team for Optimal Data Collection in Internet-of-Things Networks With Reconfigurable Intelligent Surfaces

This article considers a time-constrained data collection problem from a network of ground sensors mounted on a nonflat terrain by several unmanned aerial vehicles (UAVs). On an uneven terrain, the line-of-sight (LoS) from the sensors to the UAVs is often occluded. Ground-based reconfigurable intelligent surfaces (RISs) are used to make data collection more effective. Data are transmitted to the UAVs either directly or through the RISs. A model-predictive-control-based algorithm for UAVs navigation and data transmission is developed. The algorithm fully addresses the issue of an uneven terrain. It maximizes the amount of data sent to the UAVs within relatively short times and minimizes the energy expenditure of all the UAVs by establishing LoS connection directly or via RISs as often as possible. We present a mathematically rigorous proof of the optimality of the proposed method.

End-Cloud Collaboration Navigation Planning Method for Unmanned Aerial Vehicles Used in Small Areas.

Unmanned aerial vehicle (UAV) collaboration has become the main means of indoor and outdoor regional search, railway patrol, and other tasks, and navigation planning is one of the key, albeit difficult, technologies. The purpose of UAV navigation planning is to plan reasonable trajectories for UAVs to avoid obstacles and reach the task area. Essentially, it is a complex optimization problem that requires the use of navigation planning algorithms to search for path-point solutions that meet the requirements under the guide of objective functions and constraints. At present, there are autonomous navigation modes of UAVs relying on airborne sensors and navigation control modes of UAVs relying on ground control stations (GCSs). However, due to the limitation of airborne processor computing power, and background command and control communication delay, a navigation planning method that takes into account accuracy and timeliness is needed. First, the navigation planning architecture of UAVs of end-cloud collaboration was designed. Then, the background cloud navigation planning algorithm of UAVs was designed based on the improved particle swarm optimization (PSO). Next, the navigation control algorithm of the UAV terminals was designed based on the multi-objective hybrid swarm intelligent optimization algorithm. Finally, the computer simulation and actual indoor-environment flight test based on small rotor UAVs were designed and conducted. The results showed that the proposed method is correct and feasible, and can improve the effectiveness and efficiency of navigation planning of UAVs.

Research on Inertial Navigation Technology of Unmanned Aerial Vehicles with Integrated Reinforcement Learning Algorithm

With the continuous expansion of unmanned aerial vehicle (UAV) applications, traditional inertial navigation technology exhibits significant limitations in complex environments. In this study, we integrate improved reinforcement learning (RL) algorithms to enhance existing unmanned aerial vehicle inertial navigation technology and introduce a modulated mechanism (MM) for adjusting the state of the intelligent agent in an innovative manner [1,2]. Through interaction with the environment, the intelligent machine can learn more effective navigation strategies [3]. The ultimate goal is to provide a foundation for autonomous navigation of unmanned aerial vehicles during flight and improve navigation accuracy and robustness. We first define appropriate state representation and action space, and then design an adjustment mechanism based on the actions selected by the intelligent agent. The adjustment mechanism outputs the next state and reward value of the agent. Additionally, the adjustment mechanism calculates the error between the adjusted state and the unadjusted state. Furthermore, the intelligent agent stores the acquired experience samples containing states and reward values in a buffer and replays the experiences during each iteration to learn the dynamic characteristics of the environment. We name the improved algorithm as the DQM algorithm. Experimental results demonstrate that the intelligent agent using our proposed algorithm effectively reduces the accumulated errors of inertial navigation in dynamic environments. Although our research provides a basis for achieving autonomous navigation of unmanned aerial vehicles, there is still room for significant optimization. Further research can include testing unmanned aerial vehicles in simulated environments, testing unmanned aerial vehicles in realworld environments, optimizing the design of reward functions, improving the algorithm workflow to enhance convergence speed and performance, and enhancing the algorithm's generalization ability. It has been proven that by integrating reinforcement learning algorithms, unmanned aerial vehicles can achieve autonomous navigation, thereby improving navigation accuracy and robustness in dynamic and changing environments [4]. Therefore, this research plays an important role in promoting the development and application of unmanned aerial vehicle technology.

Performance Analysis and System Implementation for Energy-Efficient Passive UAV Radar Imaging System

Due to the superior flexibility and cost-efficiency, unmanned aerial vehicle (UAV) is becoming an indispensable platform for advanced remote sensing applications. In this paper, the performance and implementation of the energy-efficient passive UAV radar imaging system is investigated. Equipped with a synthetic aperture radar (SAR) receiver, the UAV platform passively reuses the backscattered signal of an external illuminator, and achieves SAR imaging and data communication. Firstly, we present the system concept and block diagram. Then, the imaging performance and feasibility are analyzed for the typical illuminators. It is found that the system can achieve distinct mission performance with different kinds of illuminators, which offers more alternatives for various mission requirements. A set of mission performance evaluators is established to comprehensively assess the capability of the system, including UAV navigation, passive SAR imaging and communication. An energy-efficient path planning method is then presented to generate a UAV path with optimized mission performance. Numerical simulations are conducted to verify the effectiveness of the performance evaluators and path planning method. Finally, a real implementation of the system is given. The imaging results of an airborne passive SAR experiment using external illuminator further validates the imaging capability and performance analysis of the system.

Convolutional neural network for UAV image processing and navigation in tree plantations based on deep learning

Abstract In this study, we show a new way for a small unmanned aerial vehicle (UAV) to move around on its own in the plantations of the tree using a single camera only. To avoid running into trees, a control plan was put into place. The detection model looks at the image heights of the trees it finds to figure out how far away they are from the UAV. It then looks at the widths of the image between the trees without any obstacles to finding the largest space. The purpose of this research is to investigate how virtual reality (VR) may improve student engagement and outcomes in the classroom. The emotional consequences of virtual reality on learning, such as motivation and enjoyment, are also explored, making this fascinating research. To investigate virtual reality’s potential as a creative and immersive tool for boosting educational experiences, the study adopts a controlled experimental method. This study’s most significant contributions are the empirical evidence it provides for the efficacy of virtual reality in education, the illumination of the impact VR has on various aspects of learning, and the recommendations it offers to educators on how to make the most of VR in the classroom.

Cross-Modal Images Matching Based Enhancement to MEMS INS for UAV Navigation in GNSS Denied Environments

A new cross-modal image matching method is proposed to solve the problem that unmanned aerial vehicles (UAVs) are difficult to navigate in GPS-free environment and night environment. In this algorithm, infrared image or visible image is matched with satellite visible image. The matching process is divided into two steps, namely, coarse matching and fine alignment. Based on the dense structure features, the coarse matching algorithm can realize the position update above 10 Hz with a small amount of computation. Based on the end-to-end matching network, the fine alignment algorithm can align the multi-sensor image with the satellite image under the condition of interference. In order to obtain the position and heading information with higher accuracy, the fusion of the information after visual matching with the inertial information can restrain the divergence of the inertial navigation position error. The experiment shows that it has the advantages of strong anti-interference ability, strong reliability, and low requirements on hardware, which is expected to be applied in the field of unmanned navigation.

Retraction: Al Said, N, Gorbachev, Y, Avdeenko, A. An unmanned aerial vehicles navigation system on the basis of pattern recognition applications—Review of implementation options and prospects for development. Software: Practice and Experience 2021; 51: 1509–1517. https://doi.org/10.1002/spe.2964

The above article, published online on July 2021 in Wiley Online Library https://onlinelibrary.wiley.com/doi/10.1002/spe.2964 has been retracted by agreement between the journal's Editor‐in‐Chief and John Wiley & Sons Ltd.The retraction has been agreed following concerns regarding manipulation of the peer review and publishing process. Concerns were originally raised by a third party (1). Further investigation by the publisher has found manipulation of the peer review process. The retraction has been agreed because the peer review of the article was compromised. The authors disagree with this retraction. Abalkina, A. (2022). Publication and collaboration anomalies in academic papers originating from a paper mill: evidence from a Russia‐based paper mill https://arxiv.org/abs/2112.13322

Large field-of-view thermal imaging via all-silicon meta-optics.

A broad range of imaging and sensing technologies in the infrared require large field-of-view (FoV) operation. To achieve this, traditional refractive systems often employ multiple elements to compensate for aberrations, which leads to excess size, weight, and cost. For many applications, including night vision eye-wear, air-borne surveillance, and autonomous navigation for unmanned aerial vehicles, size and weight are highly constrained. Sub-wavelength diffractive optics, also known as meta-optics, can dramatically reduce the size, weight, and cost of these imaging systems, as meta-optics are significantly thinner and lighter than traditional refractive lenses. Here, we demonstrate 80° FoV thermal imaging in the long-wavelength infrared regime (8-12µm) using an all-silicon meta-optic with an entrance aperture and lens focal length of 1cm.

Efficient UAV path planning using coverage map‐based value iteration

AbstractThis letter presents an efficient coverage map‐based unmanned aerial vehicle (UAV) navigation framework in cellular communication systems. Unlike previous research that focused on viewing UAV navigation as a Markov decision process in unknown continuous state space and leveraged various model‐free and deep neural network‐based reinforcement learning algorithms, a more straightforward and efficient model‐based value iteration algorithm is proposed. The algorithm leverages prior knowledge obtained through empirical channel models to develop a sampled coverage map that can be used in value iteration. A deep neural network is subsequently trained with supervised learning to approximate the optimal Q function in continuous state space. Finally, the trained neural network is applied to obtain a UAV trajectory that optimizes the objective function.

Analysis of navigation system accuracy characteristics for micro UAVs

The article analyzes the noise influence of the main types that arise in the process of exchanging navigational information between the GPS receiver of an micro-class unmanned aerial vehicle and the global satellite navigation system using an improved advanced simulation model in the Matlab – Simulink software environment, which allows building a representative statistical model in the process designing algorithms of the navigation system of unmanned aerial vehicles. With the help of modeling the process of choosing the receiver gain factor of an unmanned aerial vehicle and the study of the influence of the quality of reception and processing navigation signals during the increase of the distance relative to the satellite signal of the global navigation satellite system, it was established that with an increase in the gain factor of the antenna, the noise level decreases. However, an increase in the amplification factor leads to an increase in the dimensions of the antenna, as well as, accordingly, an increase in energy consumption, which does not meet the requirements for the mass-dimensional indicators of the microclass of unmanned aerial vehicles. Also, the article investigated the operation process of microelectromechanical systems of platformless inertial navigation systems, namely, at the moment of the disappearance of global satellite systems at a time interval of up to 300 seconds, to determine the error of calculating the parameter of the vertical component (height) and vertical speed of an unmanned aerial vehicle. According to the simulation results, it was found that the orientation and navigation of unmanned aerial vehicles in autonomous flight depend significantly on random errors of microelectromechanical systems of platformless inertial navigation systems, these include random angle wandering (zero noise drift); the influence of linear acceleration of the accelerometer sensor, by studying the noise model of errors microelectromechanical systems to determine the eight velocity parameter in autonomous flight mode, which is of a significant nature.

Advanced Control Techniques for Unmanned Aerial Vehicle (UAV) Navigation and Flight Control

Advanced Control Techniques for Unmanned Aerial Vehicle (UAV) Navigation and Flight Control

A Deep-Learning-Based GPS Signal Spoofing Detection Method for Small UAVs

The navigation of small unmanned aerial vehicles (UAVs) mainly depends on global positioning systems (GPSs). However, GPSs are vulnerable to attack by spoofing, which causes the UAVs to lose their positioning ability. To address this issue, we propose a deep learning method to detect the spoofing of GPS signals received by small UAVs. Firstly, we describe the GPS signal dataset acquisition and preprocessing methods; these include the hardware system of the UAV and the jammer used in the experiment, the time and weather conditions of the data collection, the use of Spearman correlation coefficients for preprocessing, and the use of SVM-SMOTE to solve the spoofing data imbalance. Next, we introduce a PCA-CNN-LSTM model. We used principal component analysis (PCA) of the model to extract feature information related to spoofing from the GPS signal dataset. The convolutional neural network (CNN) in the model was used to extract local features in the GPS signal dataset, and long short-term memory (LSTM) was used as a posterior module of the CNN for further processing and modeling. To minimize randomness and chance in the simulation experiments, we used the 10-fold cross-validation method to train and evaluate the computational performance of our spoofing machine learning model. We conducted a series of experiments in a numerical simulation environment and evaluated the proposed model against the most advanced traditional machine learning and deep learning models. The results and analysis show that the PCA-CNN-LSTM neural network model achieved the highest accuracy (0.9949). This paper provides a theoretical basis and technical support for spoofing detection for small-UAV GPS signals.

Unmanned aerial vehicle navigation in underground structure inspection: A review

Many years after construction, a number of existing old tunnels and underground structures are deteriorating with time as evidenced by cracks, large deformations, water leakage and so forth, which usually require regular site inspections to record their structural deterioration by taking high‐pixel, high‐overlap images along miles of a tunnel network. For complex underground structures (e.g., long tunnels and large caves), unmanned aerial vehicles (UAVs) may be adaptive in acquiring images at multiple heights and angles with low operational costs. So far, UAV underground structural health monitoring has become mature for open‐air surveying with rapid developments in robotic software and hardware. However, the UAV image acquisition for underground working conditions still faces a number of key challenges. This paper aims to provide an overview of UAV navigation techniques in confined dark spaces for geotechnical engineers, geologists, drone developers and other interdisciplinary researchers & professionals in the structural health monitoring field. It specifies the challenges for UAV application in underground space, mainly including lack of Global Navigation Satellite System (GNSS) signals, poor lighting conditions, weak features and obstacle avoidance and then followed by strategic solutions. For example, in light of poor GNSS signals, the fusion of multi‐sensors (e.g., laser imaging, detection and ranging (LiDAR) and multi‐cameras) can enhance localization accuracy in low‐luminance underground conditions. To address obstacle avoidance, computer vision (CV)‐based navigation algorithms (e.g., deep reinforced learning [DRL]) enable effective navigation in complex 3D spaces, but their adaptability is limited by arithmetic power and pre‐training needs. The review of relevant previous studies concludes that further development for UAVs in underground space inspection may focus on operation in large‐scale geometric inspection environments, obstacle avoidance, features and semantic recognition.

DWPIS: Dynamic-Weight Parallel Instance and Skeleton Network for Railway Centerline Detection

The primary premise of autonomous railway inspection using unmanned aerial vehicles is achieving autonomous flight along the railway. In our previous work, fitted centerline-based unmanned aerial vehicle (UAV) navigation is proven to be an effective method to guide UAV autonomous flying. However, the empirical parameters utilized in the fitting procedure lacked a theoretical basis and the fitted curves were also not coherent nor smooth. To address these problems, this paper proposes a skeleton detection method, called the dynamic-weight parallel instance and skeleton network, to directly extract the centerlines that can be viewed as skeletons. This multi-task branch network for skeleton detection and instance segmentation can be trained end to end. Our method reformulates a fused loss function with dynamic weights to control the dominant branch. During training, the sum of the weights always remains constant and the branch with a higher weight changes from instance to skeleton gradually. Experiments show that our model yields 93.98% mean average precision (mAP) for instance segmentation, a 51.9% F-measure score (F-score) for skeleton detection, and 60.32% weighted mean metrics for the entire network based on our own railway skeleton and instance dataset which comprises 3235 labeled overhead-view images taken in various environments. Our method can achieve more accurate railway skeletons and is useful to guide the autonomous flight of a UAV in railway inspection.

A Hybrid Human-in-the-Loop Deep Reinforcement Learning Method for UAV Motion Planning for Long Trajectories with Unpredictable Obstacles

Unmanned Aerial Vehicles (UAVs) can be an important component in the Internet of Things (IoT) ecosystem due to their ability to collect and transmit data from remote and hard-to-reach areas. Ensuring collision-free navigation for these UAVs is crucial in achieving this goal. However, existing UAV collision-avoidance methods face two challenges: conventional path-planning methods are energy-intensive and computationally demanding, while deep reinforcement learning (DRL)-based motion-planning methods are prone to make UAVs trapped in complex environments—especially for long trajectories with unpredictable obstacles—due to UAVs’ limited sensing ability. To address these challenges, we propose a hybrid collision-avoidance method for the real-time navigation of UAVs in complex environments with unpredictable obstacles. We firstly develop a Human-in-the-Loop DRL (HL-DRL) training module for mapless obstacle avoidance and secondly establish a global-planning module that generates a few points as waypoint guidance. Moreover, a novel goal-updating algorithm is proposed to integrate the HL-DRL training module with the global-planning module by adaptively determining the to-be-reached waypoint. The proposed method is evaluated in different simulated environments. Results demonstrate that our approach can rapidly adapt to changes in environments with short replanning time and prevent the UAV from getting stuck in maze-like environments.

A power line segmentation model in aerial images based on an efficient multibranch concatenation network

Inspection of a power transmission line by an unmanned aerial vehicle (UAV) is an important measure to ensure the operational safety of the power grid. A semantic segmentation model based on deep learning can assist UAVs in extracting power lines, which is a crucial task to ensure the safe navigation of UAVs. However, the existing models are vulnerable to complex background interference in aerial images and the thin structure of power lines. To solve these problems, an improved power line segmentation model based on Deeplabv3+ (PL-Deeplab) is proposed in this paper. To create our model, the multibranch concatenation network (MCNet) with stronger feature extraction capability is introduced to the backbone network. Then, we design a one-shot aggregation feature pyramid (OSAFP) to effectively extract the contextual information and provide a larger receptive field. Furthermore, the feature fusion module (FFM) in the decoder is used to increase the utilization of high-low level feature information and improve the ability of the model to accurately segment the boundaries of power lines. In addition, the weighted loss function is used to solve the problem of class imbalance in the power lines dataset. A large number of experiments on the power lines public dataset show that the proposed model can complete the power line inspection task better and provide security for the UAV power line inspection.

Opportunistic Autonomous Integrity Monitoring for Enhanced UAV Safety

An opportunistic advanced receiver autonomous integrity monitoring (OARAIM) algorithm for unmanned aerial vehicle (UAV) navigation is developed. This algorithm fuses ambient terrestrial signals of opportunity (SOPs) with global navigation satellite system (GNSS) signals to improve the capability of detecting GNSS and SOP measurement faults and provide tight protection level (PL) bounds. A receiver is assumed to make pseudorange measurements on multiple GNSS satellites and terrestrial SOPs. Experimental tests are presented injecting simulated faults into the OARAIM algorithm, which successfully detects the faults in GPS satellites and SOPs. Moreover, the OARAIM algorithm and the inclusion of the SOPs reduces the vertical and horizontal PLs by more than 55% and 70%, respectively, compared to only using GNSS measurements.