Here, we propose a CNN-based infrared image enhancement method to transform pseudo-realistic regions of simulation-based infrared images into real infrared texture. The proposed algorithm consists of ...the following three steps. First, target infrared features based on a real infrared image are extracted through pretrained VGG-19 networks. Next, by implementing a neural style-transfer algorithm to a simulated infrared image, fractal nature features from the real infrared image are progressively applied to the image. Therefore, the fractal characteristics of the simulated image are improved. Finally, based on the results of fractal analysis, peak signal-to-noise (PSNR), structural similarity index measure (SSIM), and natural image quality evaluator (NIQE) texture evaluations are performed to know how the simulated infrared image is properly transformed as it contains the real infrared fractal features. We verified the proposed methodology using a simulation with three different simulation conditions with a real mid-wave infrared (MWIR) image. As a result, the enhanced simulated infrared images based on the proposed algorithm have better NIQE and SSIM score values in both brightness and fractal characteristics, indicating the closest similarity to the given actual infrared image. The proposed image fractal feature analysis technique can be widely used not only for the simulated infrared images but also for general synthetic images.
The complex and dynamic space environment is both exciting and challenging in this NewSpace era. In particular, Low-Earth Orbits are being realigned and reinvented for various purposes using suitable ...technological advancement. This paper is focused on the major parameters that can be analyzed to attain orbit control and autonomy of small-satellite constellations for real-time applications. By applying industry experience to graduate research, this work addresses the related concerns in a realistic manner. Currently, global small-satellite constellation solutions are too expensive and inaccessible for many nations to help in their data reception requirements. This issue was addressed, and some of the main aspects relating to low-cost and high-benefit technical synthesis, in addition to utilization for deep-space missions, were also discussed in detail. In conclusion, this paper demonstrated a strategic approach to optimize the coverage and performance, and reduce the cost of small-satellite constellations, compared with present day constellations, allowing the data to be relayed faster and with precision. This will benefit the industry in the development of low-cost constellations, and effectively assist in disaster management and deep-space communication relays. Autonomous orbit selection and navigation can be established for better path alignment for satellites to efficiently propagate and deliver the required data.
Star Trackers are often the most accurate instrument in an Attitude Determination and Control Systems, but often present a slow update rate, requiring additional sensor and sensor fusion algorithms ...to provide a smoother and faster output. However, the available rate gyros are either noisy, or expensive and heavy. The proposed work investigates the feasibility of high-speed star trackers with modern optics, sensors, and computing systems. Firstly, we investigate the sensitivity of an optoelectrical acquisition system stimulated by dim stars, secondly, we propose and evaluate an algorithm designed to operate at high speed and to be compatible with an Field-Programmable Gate Array implementation, before evaluating the performance of the implementation on FPGA. Finally, we debate the usability of such a system, both in terms of compatibility with a mission and CubeSat ecosystems, and in terms of performance. As a result, aside from removing the need for a rate gyro, Attitude Determination and Control Systems overall pointing performances can be increased. The proposed attitude determination system achieved a 0.001° accuracy, with a 99.1% sky coverage and an ability to reject false-positive while performing a single-frame lost-in-space star identification at a 50 Hz update rate with a total delay of 19 ms, including 13 ms.
In the work reported in this paper, a lost-in-space star pattern identification algorithm for agile spacecraft was studied. Generally, the operation of a star tracker is known to exhibit serious ...degradation or even failure during fast attitude maneuvers. While tracking methods are widely used solutions to handle the dynamic conditions, they require prior information about the initial orientation. Therefore, the tracking methods may not be adequate for autonomy of attitude and control systems. In this paper a novel autonomous identification method for dynamic conditions is proposed. Additional constraints are taken into account that can significantly decrease the number of stars imaged and the centroid accuracy. A strategy combining two existing classes for star pattern identification is proposed. The new approach is intended to provide a unique way to determine the identity of stars that promises robustness against noise and rapid identification. Moreover, representative algorithms implemented in actual space applications were utilized as counterparts to analyze the performance of the proposed method in various scenarios. Numerical simulations show that the proposed method is not only highly robust against positional noise and false stars, but also guarantees fast run-time, which is appropriate for high-speed applications.
Terrain-aided navigation (TAN) is a technology that estimates the position of the vehicle by comparing the altitude measured by an altimeter and height from the digital elevation model (DEM). The ...particle filter (PF)-based TAN has been commonly used to obtain stable real-time navigation solutions in cases where the unmanned aerial vehicle (UAV) operates at a high altitude. Even though TAN performs well on rough and unique terrains, its performance degrades in flat and repetitive terrains. In particular, in the case of PF-based TAN, there has been no verified technique for deciding its terrain validity. Therefore, this study designed a Rao-Blackwellized PF (RBPF)-based TAN, used long short-term memory (LSTM) networks to endure flat and repetitive terrains, and trained the noise covariances and measurement model of RBPF. LSTM is a modified recurrent neural network (RNN), which is an artificial neural network that recognizes patterns from time series data. Using this, this study tuned the noise covariances and measurement model of RBPF to minimize the navigation errors in various flight trajectories. This paper designed a TAN algorithm based on combining RBPF and LSTM and confirmed that it can enable a more precise navigation performance than conventional RBPF based TAN through simulations.
Spacecraft relative pose estimation for an uncooperative spacecraft is challenging because the target spacecraft neither provides sensor information to a chaser spacecraft nor contains markers that ...assist vision-based navigation. Moreover, the chaser does not have prior pose estimates when initiating the pose estimation. This paper proposes a new monocular pose estimation algorithm that addresses these issues in pose initialization situations for a known but uncooperative target spacecraft. The proposed algorithm finds convexity defect features from a target image and uses them as cues for matching feature points on the image to the points on the known target model. Based on this novel method for model matching, it estimates a pose by solving the PnP problem. Pose estimation simulations are carried out in three test scenarios, and each assesses the estimation accuracy and initialization performance by varying relative attitudes and distances. The simulation results show that the algorithm can estimate the poses of spacecraft models when a solar panel length and the number of solar panels are changed. Furthermore, a scenario considering the surface property of the spacecraft emphasizes that robust feature detection is essential for accurate pose estimation. This algorithm can be used for proximity operations with a known but uncooperative target spacecraft. Specifically, one of the main applications is relative navigation for on-orbit servicing.
In recent years, target recognition technology for synthetic aperture radar (SAR) images has witnessed significant advancements, particularly with the development of convolutional neural networks ...(CNNs). However, acquiring SAR images requires significant resources, both in terms of time and cost. Moreover, due to the inherent properties of radar sensors, SAR images are often marred by speckle noise, a form of high-frequency noise. To address this issue, we introduce a Generative Adversarial Network (GAN) with a dual discriminator and high-frequency pass filter, named DH-GAN, specifically designed for generating simulated images. DH-GAN produces images that emulate the high-frequency characteristics of real SAR images. Through power spectral density (PSD) analysis and experiments, we demonstrate the validity of the DH-GAN approach. The experimental results show that not only do the SAR image generated using DH-GAN closely resemble the high-frequency component of real SAR images, but the proficiency of CNNs in target recognition, when trained with these simulated images, is also notably enhanced.
This study proposed a novel nonlinear blended aerodynamic model for the tiltrotor unmanned aerial vehicle (UAV) during the transition phase to handle the high angle-of-attack (AoA) flight, which ...aggregated the flat-plate mode and the linear mode of the aerodynamic coefficients. Additionally, a harmonic disturbance observer (HDO) and super-twisting sliding mode controller (STSMC) addressed the fast-changing external disturbances and attenuated the chattering problem in the original SMC. The comparative trajectory tracking results indicated that the blended aerodynamic model accurately tracks the reference signals with no tracking errors, which demonstrated a superior performance as compared to the traditional aerodynamic model, with a reduction of 2.2%, 50%, 73.6%, and 11.2% in the time required for tracking the pitch angle, pitch rate, and velocities u and w, respectively. Conversely, the traditional one exhibited significant tracking errors, ranging from 0.016° in the pitch angle channel to 1.25°/s in the pitch rate channel, and 0.6 m/s for velocity u and 0.01 m/s for velocity w. Moreover, the comparative control input results illustrated that the least control effort was required for the proposed HDO-STSMC control scheme with a blending function, while the original ESO-SMC experienced more oscillations and sharp amplitude changes, taking twice the time to converge, with considerable tracking errors such as 1.067° in the pitch angle channel, 0.788°/s in the pitch rate channel, 1.554 m/s for velocity u, and 0.746 m/s for velocity w, which verified the feasibility and superiority of the proposed HDO-STSMC with the blending function. Two performance indices revealed the robust stability and rapid convergence of the proposed transition blended aerodynamic model with the HDO-STSMC control scheme.
This paper presents the method to solve the problem of path planning for an unmanned aerial vehicle (UAV) in adversarial environments including radar-guided surface-to-air missiles (SAMs) and unknown ...threats. SAM lethal envelope and radar detection for SAM threats and line-of-sight (LOS) calculation for unknown threats are considered to compute the cost for path planning. In particular, dynamic SAM lethal envelope is taken into account for path planning in that SAM lethal envelope does change its direction according to the flight direction of UAV. In addition, terrain masking, nonisotropic radar cross section (RCS), and dynamic constraints of UAV are considered to determine the cost of the path. An improved particle swarm optimization (PSO) algorithm is proposed for finding an optimal path. The proposed algorithm is composed of preprocessing steps, multi-swarm PSO algorithm, and postprocessing steps. The Voronoi diagram and Dijkstra algorithm as preprocessing steps provide the initial path for the multi-swarm PSO algorithm which uses multiple swarms with sub-swarms for the balance between exploration and exploitation. Postprocessing steps include waypoint insertion and 3D path smoothing. The computation time is reduced by using the map generation, the coordinate transformation, and the graphic processing unit (GPU) implementation of the algorithm. Various simulations are carried out to compare the performance of the proposed method according to the number of iterations, the number of swarms, and the number of cost evaluation points. The t-test results show that the suggested method is statistically better than existing methods.
A star pattern identification algorithm, called modified grid algorithm, for attitude determination of spacecraft is addressed. The proposed algorithm is closely connected to a general pattern ...recognition technique. Each star is characterized by a well-defined pattern that can be determined by the surrounding stars. The so-called grid algorithm is one of the star identification algorithms based upon the pattern recognition approach. The proposed algorithm, is motivated by the conventional grid algorithm. To enhance the performance of the conventional grid algorithm, a modified method using polar grid, virtual grid, and multi-references is proposed. Simulation study is conducted for the demonstration of the new algorithm. The proposed modified grid approach turns out to make the grid algorithm more robust and reliable.