Unmanned Aerial Vehicle Target Research Articles

SIMULATION APPROVAL OF INFORMATION TECHNOLOGY OF OPTICAL CHANNEL AIRCRAFT NAVIGATION

Experience in modern combat operations — including Eastern Ukraine — shows the effectiveness of reconnaissance unmanned aerial vehicles (UAVs) usage. An obvious way to navigate UAVs is to navigate with using GPS. Thereby, an effective countermeasure against UAVs is radio-frequency suppression of the GPS signal, which in turn raises the issue of autonomous UAV navigation, in particular with the usage of data from the UAV’s payload cameras. That is, the current direction of development of reconnaissance unmanned aerial vehicles (UAVs) is the development of new methods and algorithms for alternative navigation on the optical channel by terrain recognizing and determining coordinates in real time from the cameras of the target UAV only. The basis for solving this problem in terms of information technology are object search methods for known images in a digital image. In another way, considering the method of UAV navigation by the optical channel in combination with the task of developing the appropriate software and hardware complex (SHC), one of the stages of the mentioned process is the developed components testing. The publications analysis shows insufficient coverage of this aspect of the SHCs development. The goal of this article is to describe the process of simulation testing of the UAV optical channel navigation method by developing the corresponding software. Considering the complexity of the approbation process on UAV directly, as well as significant economic and/or time loss in case of failure, it makes sense to perform simulation on test data. In this publication: the software for simulation approbation of navigation technology of the aircraft optical channel is developed, the simulation approbation by usage of it is performed, the correctness of work of the offered navigation technology is confirmed.

The Design And Build of Telemetry system Portable Ground Control Station (GCS) as Control and Monitoring on Unmanned Aerial Vehicle (UAV) Aircraft Galak-24

Abstract – Ground Control Station (GCS) is a very important part in controlling and monitoring UAV aircraft as well as monitoring a mission so that operators at the home base can send mission orders. The importance of this mission requires a system in this case, namely the GCS that can be connected to various types of unmanned vehicles. This study develops a GCS system that is used for controlling and monitoring the condition of UAV aircraft and sending waypoint tracking mission commands that are connected to a cloud server via the internet. This system consists of two units, namely the flight unit and the video unit, the flight unit consists of a flight controller, the video unit is a system that is on a camera connected to telemetry and connected to the internet so that it can be accessed via the internet, thus controlling and monitoring UAV aircraft and target control delivery on the GCS will be accessible anywhere via the internet. The GCS system has been able to display the condition of the aircraft status, sending flight hover mission commands, land and sending missions, namely tracking waypoints and camera object coordinates. In areas where the mission's 4G internet signal can run smoothly by sending 15 takeoff and landing control waypoints which manually with precision results, the fix wings type UAV aircraft can pass through several tracking waypoints that experience errors.

Multi-UAV cooperative target tracking with bounded noise for connectivity preservation

We investigate cooperative target tracking of multiple unmanned aerial vehicles (UAVs) with a limited communication range. This is an integration of UAV motion control, target state estimation, and network topology control. We first present the communication topology and basic notations for network connectivity, and introduce the distributed Kalman consensus filter. Then, convergence and boundedness of the estimation errors using the filter are analyzed, and potential functions are proposed for communication link maintenance and collision avoidance. By taking stable target tracking into account, a distributed potential function based UAV motion controller is discussed. Since only the estimation of the target state rather than the state itself is available for UAV motion control and UAV motion can also affect the accuracy of state estimation, it is clear that the UAV motion control and target state estimation are coupled. Finally, the stability and convergence properties of the coupled system under bounded noise are analyzed in detail and demonstrated by simulations.

Linear model predictive control for vision-based UAV pursuit

This article develops and implements a vision-based unmanned aerial vehicle (UAV)-to-UAV pursuit system using a commercial off-the-shelf Parrot AR.Drone 2.0 quadrotor. This technology is intended as a countermeasure to rogue drones carrying out activities such as flying in restricted airspace, performing unauthorized aerial videography, transporting contraband and other criminal activities, or being used as improvised weapons. The proposed approach offers benefits over other current solutions, such as wide-area radio-frequency jamming that interferes with regular communication devices or high-energy military laser systems that are expensive and time consuming to set up. A linear dynamics model of the AR.Drone 2.0 vehicle stabilized by its onboard feedback control system is derived, and its parameters are experimentally identified. A linear model predictive control is developed to track specified flight trajectories, then implemented and validated in hardware flight tests. Detection and ranging of the target UAV from the pursuer UAV’s onboard monocular camera are performed using the YOLO v2 convolutional neural network algorithm. The combined control and vision design is implemented in hardware and tested quantitatively in flight experiments.

Signal-domain Kalman filtering: An approach for maneuvering target surveillance with wideband radar

As unmanned aerial vehicles (UAVs), owing to their low cost and wide variety of applications, become increasingly indispensable to modern society, and monitoring their illegal use through multichannel radar tracking has drawn widespread attention. Unfortunately, traditional tracking methods face challenges due to the UAV target with high-maneuverability and low-observability. In addition, the traditional measurements suffer some significant information loss because of their treatments like thresholding, clustering and peak sampling, which decreases tracking performance. In order to track UAV precisely, we propose a novel UAV tracking method based on the joint estimation of range and direction of arrival (DOA) in this paper. A complex-valued reference signal is introduced by coherently integrating in sliding windows to obtain SNR gain and preserve the complete structure and motion information of UAV. Besides motion state, the complex-valued reference signal is also utilized to predict the current return signal based on dynamic equation, and then a Bayes based method is derived to jointly estimate the range and DOA errors by comparing reference signal and return signal. In order to adapt to the maneuverable feature, a precise measurement model for motion variables is constructed to realize tracking combined with Kalman filter. Due to the utilization of the complex-valued reference signal and the precise measurement model, the proposed method has outstanding performance in the scene of low SNR and high maneuverability. In addition, there is no any information loss when the raw data is used to realize estimating and tracking. Finally, simulated and real-measured experiments confirm its remarkable performance.

Knowledge Transfer Between Different UAVs for Trajectory Tracking

Robots are usually programmed for particular tasks with a considerable amount of hand-crafted tuning work. Whenever a new robot with different dynamics is presented, the well-designed control algorithms for the robot usually have to be re-tuned to guarantee good performance. It remains challenging to directly program a robot to automatically learn from the experiences gathered by other dynamically different robots. With such a motivation, this letter proposes a learning algorithm that enables a quadrotor unmanned aerial vehicle (UAV) to automatically improve its tracking performance by learning from the tracking errors made by other UAVs with different dynamics. This learning algorithm utilizes the relationship between the dynamics of different UAVs, named the target and training UAVs, respectively. The learning signal is generated by the learning algorithm and then added to the feedforward loop of the target UAV, which does not affect the closed-loop stability. The learning convergence can be guaranteed by the design of a learning filter. With the proposed learning algorithm, the target UAV can improve its tracking performance by learning from the training UAV without baseline controller modifications. Both numerical studies and experimental tests are conducted to validate the effectiveness of the proposed learning algorithm.

Monocular Visual SLAM Based on a Cooperative UAV-Target System.

To obtain autonomy in applications that involve Unmanned Aerial Vehicles (UAVs), the capacity of self-location and perception of the operational environment is a fundamental requirement. To this effect, GPS represents the typical solution for determining the position of a UAV operating in outdoor and open environments. On the other hand, GPS cannot be a reliable solution for a different kind of environments like cluttered and indoor ones. In this scenario, a good alternative is represented by the monocular SLAM (Simultaneous Localization and Mapping) methods. A monocular SLAM system allows a UAV to operate in a priori unknown environment using an onboard camera to simultaneously build a map of its surroundings while at the same time locates itself respect to this map. So, given the problem of an aerial robot that must follow a free-moving cooperative target in a GPS denied environment, this work presents a monocular-based SLAM approach for cooperative UAV–Target systems that addresses the state estimation problem of (i) the UAV position and velocity, (ii) the target position and velocity, (iii) the landmarks positions (map). The proposed monocular SLAM system incorporates altitude measurements obtained from an altimeter. In this case, an observability analysis is carried out to show that the observability properties of the system are improved by incorporating altitude measurements. Furthermore, a novel technique to estimate the approximate depth of the new visual landmarks is proposed, which takes advantage of the cooperative target. Additionally, a control system is proposed for maintaining a stable flight formation of the UAV with respect to the target. In this case, the stability of control laws is proved using the Lyapunov theory. The experimental results obtained from real data as well as the results obtained from computer simulations show that the proposed scheme can provide good performance.

Cooperative Pursuit Guidance to Surround Intruder Swarms Using Collision Cones

This paper addresses the problem of unmanned aerial vehicles (UAVs) pursuing a swarm of target UAVs moving on a plane. The target UAVs are assumed to be flying together as a flock. The flock is initially modeled as a circle whose radius can be time varying, and this is subsequently generalized to arbitrarily shaped swarms that may change in size. Capture is said to occur when the pursuing UAVs have successfully enclosed the target swarm within their convex hull. In subsequent scenarios, the pursuing UAVs are assumed to be carrying a rope line in an open-chain configuration, and capture is said to occur when the pursuing UAVs have (in addition to enclosing the target UAV swarm within their convex hull) also ensured that their formation approaches the target at an appropriate orientation that corresponds with the open end of the rope line. The guidance laws are developed based on a collision cone framework, using which the pursuing UAVs can cooperatively steer the velocity vector of any point in their convex hull, to intercept the target. Analytical expressions of these nonlinear cooperative pursuit guidance laws that govern the acceleration commands of the UAVs are determined. Simulations are performed using kinematic models, and they demonstrate that the pursuing UAVs are able to successfully surround the target UAV swarm.

Prediction of unmanned aerial vehicle target intention under incomplete information

The complexity and uncertainty of actual air combat and the unknown information of some air combat bring great challenges to unmanned aerial vehicle (UAV) air combat target intention prediction. In this paper, we examine the problem of air combat intention prediction under incomplete information, and present an air combat target intention prediction model based on long-short-term memory (LSTM) with incomplete information. The model adopts a hierarchical method to establish the feature set of air combat target intention prediction, encodes the information of air combat to time series features, encapsulates expert knowledge into labels, and introduces the method of fitting cubic sample interpolation function and filling average value to repair incomplete data. Also, we used the adaptive moment estimation (Adam) optimization algorithm to accelerate the training speed of the model to effectively prevent local optimum. Finally, the simulation results show that the proposed model can effectively predict the target intention of UAVs in air combat.

Optimized Stealth Design and Remolding of Target Unmanned Aerial Vehicle

In order to satisfy the imperious requirements of low-detectable target aircraft in the current test and evaluation of airborne radar and to remedy the numerous defects of magnetic microwave absorbing coating in the practical application, a new type of light-weight electric loss coating with the carbon nanotubes(CNTs) was proposed by the optimal design of the absorbent content and coating thickness. A type of target unmanned aerial vehicle(UAV) with representative non-stealth structure was remolded by the present type of coating, and the detection range of airborne radar to the remolded UAV was obtained in the flight test. The results reveal that the microwave absorbing coating with a thickness of 2.5mm has the optimized microwave absorbing properties at a CNTs content of 15wt.%, and the reflection loss value can be inferior to -8dB over the whole X band. The intensity level of scattering center of the UAV degrades after coated, and the radar cross section (RCS) of coated UAV decreases by 20dB in the flight test.

Sparse long‐time coherent integration‐based detection method for radar low‐observable manoeuvring target

Low-observable manoeuvring target detection is a challenging problem for radar signal processing, due to the complex environment, target manoeuvrability, limited observation time etc. The study proposed a novel long-time coherent integration (LTCI) method for radar manoeuvring target, especially for low-observable unmanned aerial vehicle targets. The fast non-parametric searching LTCI via a non-uniform (NU) resampling and scale processing (SP) technique is proposed, where the high-order signal phase is reduced to linear term using NU resampling. After that, the SP method is applied to realise the range migration compensation. The sparse Fourier transform (FT) and inverse FT are performed for the final integration. The manoeuvring target would appear as peaks in the non-uniformly resampling and SP-sparse LTCI domain. Experiments using two sets of real radar data indicate that the proposed method can achieve a good balance between computational cost and integration gain. In addition, detailed detection performances are compared with the traditional methods, e.g., moving target detection, fractional FT, fractional ambiguity function, Radon-based LTCIs, and sparse fractional FT.

A Novel Estimator for TDOA and FDOA Positioning of Multiple Disjoint Sources in the Presence of Calibration Emitters

Multiple-target localization is extensively applied in wireless connected networks. However, sensor location uncertainty is known to degrade significantly the target localization accuracy. Fortunately, calibration emitters such as unmanned aerial vehicles (UAV) with known location can be used to reduce the loss in localization accuracy due to sensor location errors. This paper is devoted to the use of UAV calibration emitters for time differences of arrival (TDOA) and frequency differences of arrival (FDOA) positioning of multiple targets. The study starts with deriving the Cramer-Rao bound (CRB) for TDOA/FDOA-based target location estimate when several UAV calibration signals are available. Subsequently, the paper presents an iterative constrained weighted least squares (ICWLS) estimator for multiple-target joint localization using TDOA/FDOA measurements from both target sources and UAV calibration emitters. The newly proposed method consists of two stages. In the first phase, the sensor locations are refined based on the calibration measurements as well as the prior knowledge of sensor locations. The second step provides the estimate of multiple-target locations by combining the measurements of target signals as well as the estimated values in the first phase. An efficient ICWLS algorithm is presented at each stage. Both the two algorithms are implemented by using matrix singular value decomposition (SVD), which is able to provide a closed-form solution and update the weighting matrix at every iteration. Finally, the convergence behavior and estimation mean-square-error (MSE) of the new estimator are deduced. Both theoretical analysis and simulation results show that the developed method can improve the TDOA/FDOA localization accuracy obviously with the help of UAV calibration emitters.

Machine learning based null allocation design for adaptive beamforming in unmanned aerial vehicle communications

In order to communicate with target unmanned aerial vehicles (UAVs), ground control stations (GCSs) typically adopt adaptive beamforming with high antenna gain and co-channel interference rejection. Multiple interfering signals arriving from different directions arise from other UAVs and other GCSs, and the beamformer installed in the home GCS will usually attempt to null unwanted signals from all these directions of arrival (DoAs) without analyzing the distribution of the angles of arrival. Consequently, the beamformer will fail to allocate nulls in some directions, and the signal-to-interference-plus-noise (SINR) performance of the home GCS is impaired. In this paper, a new approach to null allocation is proposed, based on machine learning using k-means clustering. The design first involves the collection of information about the DoAs and the corresponding received signal strengths of all the interfering signals into a two-dimensional dataset. Secondly, this dataset is broken down into clusters by using k-means clustering, and the cluster centroids are calculated. In each cluster, the interfering signal that has the shortest Euclidean distance to the centroid is identified as the approximated centroid. Only the approximated centroids are selected as input to the beamformer, with the aim that each complete cluster of interference sources can be nulled by allocating one null per cluster. To optimize the number of clusters k used in the null allocation process, the design adopts the particle swarm optimization technique to adaptively update the value of k to maximize the SINR at the home GCS. Simulation results show that our design yields a maximum SINR improvement of about 12 dB when compared to cases where no null allocation is considered. Moreover, our design also outperforms null steering in the UAV scenarios. Advantageously, this enhanced performance is obtained without the need for additional power amplification or hardware modification to the beamformer.

Implementation and optimization of the cascade classifier algorithm for UAV detection and tracking

A number of vision-based algorithms designed to detect and track unmanned aerial vehicles (UAVs) from on board a second UAV have been researched, implemented, and experimentally validated over the last decade. However, the successful methods have tended to rely on characteristics such as color or shape, meaning they require the target UAV to have particular markings or geometries. This paper uses the Viola–Jones cascade classifier, a computer vision algorithm originally designed to detect human faces in video streams, and demonstrates its capability for detecting and tracking an arbitrary type of UAV with excellent performance in either indoor or outdoor environments and with a variety of backgrounds. The Viola–Jones algorithm is applied to two specific quadrotor UAV models, the Solo from 3D Robotics and the AR.Drone 2.0 from Parrot. Experimental testing demonstrates that the resulting system achieves very good detection and tracking performance in real time on each UAV type for both indoor and outdoor flight tests.

Tilted-Beam Switched Array Antenna for UAV Mounted Radar Applications with 360° Coverage

A highly efficient antenna array for unmanned aerial vehicle (UAV) mounted radar applications with a tilted-beam characteristic and a 360° beam coverage is proposed in this paper. The proposed array antenna is configured by four planar super J-pole antennas with 2-dimensional ground reflectors. Each super J-pole antenna element provides a high directivity where the peak gain is tilted about 45° facing toward the ground from the bottom of a UAV body. Thus, the air-to-ground communication difficulty due to the altitude difference between the UAV and ground targets can be effectively solved. Further, the four super J-pole elements with a switched operation can cover the whole 360° areas around the UAV while high antenna gain is maintained. To verify the performance, the proposed structure was implemented at 5.9 GHz with an overall volume of 0.88 × 0.88 × 0.83 λo3. The measured 10-dB impedance bandwidths for all four antenna elements were better than 27.2% and the isolation among the four antenna ports was also always better than 13 dB. The measured peak gain was better than 7.4 dBi and tilted at 45° in the elevation angle. Lastly, the measured half power beam widths in elevation and azimuth planes were more than 60° and 87°, respectively.

Design of airborne target tracking accelerator based on KCF

The on-board target tracking of unmanned aerial vehicle (UAV) relies on on-board computer to process the collected ground image information, and then use the target tracking algorithm to achieve the target tracking function, which provides the user with target position, trajectory and other information. UAVs are limited by load and power consumption. Due to the high resolution and frame rate of UAV's image collection system, traditional target tracking platforms cannot meet the requirements. As a result, the real-time nature of the tracking platform urgently needs to be resolved. This study designs and implements the airborne ground target tracking accelerator for UAV. The kernelised correlation filters (KCFs) algorithm with low computational complexity and precision is selected to achieve the airborne ground target tracking function and its performance bottleneck is analysed. In order to improve the real-time performance of the tracking task processing, the ZYNQ platform based on ARM and field programmable gate arrays is chosen to achieve the hardware acceleration of the KCF algorithm. The KCF algorithm is implemented in hardware using the high-level synthesis technology, and a high-speed data transmission link is established. Experiments show that the design can achieve a tracking rate of more than 30 FPS under 960 × 540 resolution, which meets the real-time requirements of UAV target tracking task.

Meteorological clutter suppression method for ball‐borne radar based on Kalmus filter

Aimed at the problem that the unmanned aerial vehicle (UAV) target is difficult to be detected in the meteorological clutter because of their close velocity, a new detection method is proposed for the ball-borne radar based on Kalmus filter. Firstly, the radar echo is compressed by pulse compression. Then, the meteorological clutter is filtered out by the velocity-corrected Kalmus filter. Finally, CFAR is employed for detection. The simulation results show that this method can effectively suppress the meteorological clutter and improve the detection performance of the ball-borne radar to UAV target.

THE RESEARCH OF UNMANNED AIRCRAFT EVASIVE MANEUVERS FROM ATTACK BY ENEMY AIRCRAFT ON THE BASIS OF THE GAME APPROACH

Actual level of unmanned aerial vehicles development allows us to consider them as an effective tool for solving a variety of civil and military tasks (primarily reconnaissance and strike). At the same time, one of the most important problems associated with the combat use of unmanned aerial vehicles remains to ensure their high survivability in organized counteraction conditions, the source of which can be both ground-based air defense and fighter aircraft (manned or unmanned). For this reason, the study and optimization of unmanned aerial vehicle evasion maneuvers from an enemy air attack remains relevant. In the article on the basis of game approach the algorithm of the unmanned aerial vehicle trajectory guaranteeing management providing its evasion from attack of the air opponent is offered. The study of unmanned aerial vehicle maneuverability tactically significant indicators influence on the effectiveness of the evasion maneuver. The results of simulation, demonstrated the influence of unmanned aerial vehicle maneuvering capabilities on achievement a positional advantage in order to solve the problem of evasion from enemy air attack, are presented. A series of computational experiments, whose results allow to assert that the use of the developed algorithm to guarantee control regardless of the relative initial state target UAV (Unmanned Aerial Vehicle) and UAV-interceptor with the comparability of their maneuvering capabilities in 73 % of cases provides the positional advantage of the target UAV, the UAV position relative to the interceptor makes inefficient use of the latest posted guided missiles, are performed. Note that the increase in the values of tactical indicators that reflect the maneuverability of the attacked UAV compared to the enemy, leads to the fact that in all cases, regardless of the initial position of the attacked UAV relative to the UAV-interceptor, it is ensured that it is brought beyond the zone of possible launches of guided missiles.

Coarse-to-Fine UAV Target Tracking With Deep Reinforcement Learning

The aspect ratio of a target changes frequently during an unmanned aerial vehicle (UAV) tracking task, which makes the aerial tracking very challenging. Traditional trackers struggle from such a problem as they mainly focus on the scale variation issue by maintaining a certain aspect ratio. In this paper, we propose a coarse-to-fine deep scheme to address the aspect ratio variation in UAV tracking. The coarse-tracker first produces an initial estimate for the target object, then a sequence of actions are learned to fine-tune the four boundaries of the bounding box. The coarse-tracker and the fine-tracker are designed to have different action spaces and operating target. The former dominates the entire bounding box and the latter focuses on the refinement of each boundary. They are trained jointly by sharing the perception network with an end-to-end reinforcement learning architecture. Experimental results on benchmark aerial data set prove that the proposed approach outperforms existing trackers and produces significant accuracy gains in dealing with the aspect ratio variation in UAV tracking. Note to Practitioners —During the past years, unmanned aerial vehicle (UAV) have gained much attention for both industrial and consumer uses. It is in urgent demand to endow the UAV with intelligent vision-based techniques, and the automatic target following via visual tracking methods as one of the most fundamental intelligent features could promote various applications of UAVs, such as surveillance, augmented reality, and behavior modeling. Nonetheless, the primary issue of a UAV-based tracking method is the platform itself: it is not stable, it tends to have sudden movements, it generates nonhomogeneous data (scale, angle, rotation, depth, and so on), all of them tend to change the aspect ratio of the target frequently and further increase the difficulty of object tracking. This paper aims to address the aspect ratio change (ARC) problem in UAV tracking. We present a coarse-to-fine strategy for UAV tracking. Specifically, the coarse bounding box is obtained to locate the target firstly. Then, a refinement scheme is performed on each boundary to further improve the position estimate. The tracker is proved to be effective to increase the resistance to the ARC. Such a method can be implemented on UAV to improve the target-following performance.

Localization and Clustering Based on Swarm Intelligence in UAV Networks for Emergency Communications

In recent years, unmanned aerial vehicle (UAV) networks have been a focus area of the academic and industrial research community. They have been used in many military and civilian applications. Emergency communication is one of the essential requirements for first responders and victims in the aftermath of natural disasters. In such scenarios, UAVs may configure ad hoc wireless networks to cover a large area. In UAV networks, however, localization and routing are challenging tasks owing to the high mobility, unstable links, dynamic topology, and limited energy of UAVs. Here, we propose swarm-intelligence-based localization (SIL) and clustering schemes in UAV networks for emergency communications. First, we propose a new 3-D SIL algorithm based on particle swarm optimization (PSO) that exploits the particle search space in a limited boundary by using the bounding box method. In the 3-D search space, anchor UAV nodes are randomly distributed and the SIL algorithm measures the distance to existing anchor nodes for estimating the location of the target UAV nodes. Convergence time and localization accuracy are improved with lower computational cost. Second, we propose an energy-efficient swarm-intelligence-based clustering (SIC) algorithm based on PSO, in which the particle fitness function is exploited for intercluster distance, intracluster distance, residual energy, and geographic location. For energy-efficient clustering, cluster heads are selected based on improved particle optimization. The proposed SIC outperforms five typical routing protocols regarding packet delivery ratio, average end-to-end delay, and routing overhead. Moreover, SIC consumes less energy and prolongs network lifetime.