Search Results (65)

The electric sail (E-sail), as an emerging propulsion system with an infinite specific impulse, is particularly suitable for ultra-long-distance multi-target deep-space exploration missions. If multiple gravity assists are considered during the exploration process, it can effectively improve the exploration efficiency of the E-sail. This paper proposes a fast optimization algorithm for deep-space multi-target exploration trajectories for the E-sail, which achieves the exploration of multiple celestial bodies and solar-system boundaries in one flight, and introduces a gravity assist to improve the flight speed of the E-sail during the exploration process. By comparing simulation examples under different conditions, the effectiveness of the algorithm proposed in this paper has been demonstrated. This is of great significance for the initial rapid design of complex deep-space exploration missions such as the E-sail multi-target exploration. Full article

The frequent launches of reusable launch vehicles are currently the primary approach to support large-scale space transportation, necessitating high reliability in recovery flights. This paper proposes a mission re-planning scheme to address throttling faults, which significantly affect the feasibility of powered landing. To quantify the influence of throttling capability, the concept of “controllable set (CS)” is introduced. The CS is defined as the collection of all feasible initial states that can achieve a successful powered landing and is computed using polyhedron approximation and convex optimization. Based on the CS, the physical feasibility of a power landing problem under deviations from the nominal conditions can be evaluated probabilistically. Besides, a deep neural network (DNN) is constructed to enhance the computational efficiency of the CS analysis, thereby meeting the requirements for online applications. Finally, an effective re-planning scheme is proposed to deal with throttling faults in recovery flight. This is achieved by adjusting the designed angle of attack during the endo-atmosphere unpowered descent phase and selecting the associated optimal handover conditions to initiate the powered landing. The optimal re-planning parameters are determined through a comprehensive investigation of the design space, leveraging probability-based CS analysis and computationally efficient DNN predictions. Simulations verify the accuracy of the CS computation algorithm and the effectiveness of the re-planning scheme under different fault conditions. The results indicate high feasibility probabilities of 99.97%, 98.12%, and 78.52% for maximum throttling capabilities at 65%, 75%, and 85% of nominal thrust magnitude, respectively. Full article

Energy scheduling for hybrid unmanned aerial vehicles (UAVs) is of critical importance to their safe and stable operation. However, traditional approaches, predominantly rule-based, often lack the dynamic adaptability and stability necessary to address the complexities of changing operational environments. To overcome these limitations, this paper proposes a novel energy scheduling framework that integrates the Model Predictive Control (MPC) with a Deep Reinforcement Learning algorithm, specifically the Deep Deterministic Policy Gradient (DDPG). The proposed method is designed to optimize energy management in hydrogen-powered UAVs across diverse flight missions. The energy system comprises a proton exchange membrane fuel cell (PEMFC), a lithium-ion battery, and a hydrogen storage tank, enabling robust optimization through the synergistic application of MPC and DDPG. The simulation results demonstrate that the MPC effectively minimizes electric power consumption under various flight conditions, while the DDPG achieves convergence and facilitates efficient scheduling. By leveraging advanced mechanisms, including continuous action space representation, efficient policy learning, experience replay, and target networks, the proposed approach significantly enhances optimization performance and system stability in complex, continuous decision-making scenarios. Full article

The optimization of information transmission in unmanned aerial vehicles (UAVs) is essential for enhancing their operational efficiency across various applications. This issue is framed as a mixed-integer nonconvex optimization challenge, which traditional optimization algorithms and reinforcement learning (RL) methods often struggle to address effectively. In this paper, we propose a novel deep reinforcement learning algorithm that utilizes a hybrid discrete–continuous action space. To address the long-term dependency issues inherent in UAV operations, we incorporate a long short-term memory (LSTM) network. Our approach accounts for the specific flight constraints of fixed-wing UAVs and employs a continuous policy network to facilitate real-time flight path planning. A non-sparse reward function is designed to maximize data collection from internet of things (IoT) devices, thus guiding the UAV to optimize its operational efficiency. Experimental results demonstrate that the proposed algorithm yields near-optimal flight paths and significantly improves data collection capabilities, compared to conventional heuristic methods, achieving an improvement of up to 10.76%. Validation through simulations confirms the effectiveness and practicality of the proposed approach in real-world scenarios. Full article

Infrared small target detection (IRSTD) is the process of recognizing and distinguishing small targets from infrared images that are obstructed by crowded backgrounds. This technique is used in various areas, including ground monitoring, flight navigation, and so on. However, due to complex backgrounds and the loss of information in deep networks, infrared small target detection remains a difficult undertaking. To solve the above problems, we present a shallow feature fusion network (SFFNet) based on detection framework. Specifically, we design the shallow-layer-guided feature enhancement (SLGFE) module, which guides multi-scale feature fusion with shallow layer information, effectively mitigating the loss of information in deep networks. Then, we design the visual-Mamba-based global information extension (VMamba-GIE) module, which leverages a multi-branch structure combining the capability of convolutional layers to extract features in local space with the advantages of state space models in the exploration of long-distance information. The design significantly extends the network’s capacity to acquire global contextual information, enhancing its capability to handle complex backgrounds. And through the effective fusion of the SLGFE and VMamba-GIE modules, the exorbitant computation brought by the SLGFE module is substantially reduced. The experimental results on two publicly available infrared small target datasets demonstrate that the SFFNet surpasses other state-of-the-art algorithms. Full article

UAV technology is advancing rapidly, and variable-sweep wing UAVs are increasingly valuable because they can adapt to different flight conditions. However, conventional control methods often struggle with managing continuous action spaces and responding to dynamic environments, making them inadequate for complex multi-UAV cooperative formation control tasks. To address these challenges, this study presents an innovative framework that integrates dynamic modeling with morphing control, optimized by the multi-agent deep deterministic policy gradient for two-sweep control (MADDPG–VSC) algorithm. This approach enables real-time sweep angle adjustments based on current flight states, significantly enhancing aerodynamic efficiency and overall UAV performance. The precise motion state model for wing morphing developed in this study underpins the MADDPG–VSC algorithm’s implementation. The algorithm not only optimizes multi-UAV formation control efficiency but also improves obstacle avoidance, attitude stability, and decision-making speed. Extensive simulations and real-world experiments consistently demonstrate that the proposed algorithm outperforms contemporary methods in multiple aspects, underscoring its practical applicability in complex aerial systems. This study advances control technologies for morphing-wing UAV formation and offers new insights into multi-agent cooperative control, with substantial potential for real-world applications. Full article

Autonomous navigation of Unmanned Aerial Vehicles (UAVs) based on deep reinforcement learning (DRL) has made great progress. However, most studies assume relatively simple task scenarios and do not consider the impact of complex task scenarios on UAV flight performance. This paper proposes a DRL-based autonomous navigation algorithm for UAVs, which enables autonomous path planning for UAVs in high-density and highly dynamic environments. This algorithm proposes a state space representation method that contains position information and angle information by analyzing the impact of UAV position changes and angle changes on navigation performance in complex environments. In addition, a dynamic reward function is constructed based on a non-sparse reward function to balance the agent’s conservative behavior and exploratory behavior during the model training process. The results of multiple comparative experiments show that the proposed algorithm not only has the best autonomous navigation performance but also has the optimal flight efficiency in complex environments. Full article

Reusable launch vehicles need to face complex and diverse environments during flight. The design of rocket recovery control law based on traditional deep reinforcement learning (DRL) makes it difficult to obtain a set of network architectures that can adapt to multiple scenarios and multi-parameter uncertainties, and the performance of deep reinforcement learning algorithm depends on manual trial and error of hyperparameters. To solve this problem, this paper proposes a self-learning control method for launch vehicle recovery based on neural architecture search (NAS), which decouples deep network structure search and reinforcement learning hyperparameter optimization. First, using network architecture search technology based on a multi-objective hybrid particle swarm optimization algorithm, the proximal policy optimization algorithm of deep network architecture is automatically designed, and the search space is lightweight design in the process. Secondly, in order to further improve the landing accuracy of the launch vehicle, the Bayesian optimization (BO) method is used to automatically optimize the hyperparameters of reinforcement learning, and the control law of the landing phase in the recovery process of the launch vehicle is obtained through training. Finally, the algorithm is transplanted to the rocket intelligent learning embedded platform for comparative testing to verify its online deployment capability. The simulation results show that the proposed method can satisfy the landing accuracy of the launch vehicle recovery mission, and the control effect is basically the same as the landing accuracy of the trained rocket model under the untrained condition of model parameter deviation and wind field interference, which verifies the generalization of the proposed method. Full article

The stratospheric airship, as a near-space vehicle, is increasingly utilized in scientific exploration and Earth observation due to its long endurance and regional observation capabilities. However, due to the complex characteristics of the stratospheric wind field environment, trajectory planning for stratospheric airships is a significant challenge. Unlike lower atmospheric levels, the stratosphere presents a wind field characterized by significant variability in wind speed and direction, which can drastically affect the stability of the airship’s trajectory. Recent advances in deep reinforcement learning (DRL) have presented promising avenues for trajectory planning. DRL algorithms have demonstrated the ability to learn complex control strategies autonomously by interacting with the environment. In particular, the proximal policy optimization (PPO) algorithm has shown effectiveness in continuous control tasks and is well suited to the non-linear, high-dimensional problem of trajectory planning in dynamic environments. This paper proposes a trajectory planning method for stratospheric airships based on the PPO algorithm. The primary contributions of this paper include establishing a continuous action space model for stratospheric airship motion; enabling more precise control and adjustments across a broader range of actions; integrating time-varying wind field data into the reinforcement learning environment; enhancing the policy network’s adaptability and generalization to various environmental conditions; and enabling the algorithm to automatically adjust and optimize flight paths in real time using wind speed information, reducing the need for human intervention. Experimental results show that, within its wind resistance capability, the airship can achieve long-duration regional station-keeping, with a maximum station-keeping time ratio (STR) of up to 0.997. Full article

Large-scale solar-powered unmanned aerial vehicles possess the capacity to perform long-term missions at different altitudes from near-ground to near-space, and the huge spatial span brings strict disciplines for its attitude control such as aerodynamic nonlinearity and environmental disturbances. The design efficiency and control performance are limited by the gain scheduling of linear methods in a way, which are widely used on such aircraft at present. So far, deep reinforcement learning has been demonstrated to be a promising approach for training attitude controllers for small unmanned aircraft. In this work, a low-level attitude control method based on deep reinforcement learning is proposed for solar-powered unmanned aerial vehicles, which is able to interact with high-fidelity nonlinear systems to discover optimal control laws and can receive and track the target attitude input with an arbitrary high-level control module. Considering the risks of field flight experiments, a hardware-in-loop simulation platform is established that connects the on-board avionics stack with the neural network controller trained in a digital environment. Through flight missions under different altitudes and parameter perturbation, the results show that the controller without re-training has comparable performance with the traditional PID controller, even despite physical delays and mechanical backlash. Full article

This study presents a method for classifying landslide triggers and sizes using climate and geospatial data. The landslide data were sourced from the Global Landslide Catalog (GLC), which identifies rainfall-triggered landslide events globally, regardless of size, impact, or location. Compiled from 2007 to 2018 at NASA Goddard Space Flight Center, the GLC includes various mass movements triggered by rainfall and other events. Climatic data for the 10 years preceding each landslide event, including variables such as rainfall amounts, humidity, pressure, and temperature, were integrated with the landslide data. This dataset was then used to classify landslide triggers and sizes using deep neural networks (DNNs) optimized through genetic algorithm (GA)-driven hyperparameter tuning. The optimized DNN models achieved accuracies of 0.67 and 0.82, respectively, in multiclass classification tasks. This research demonstrates the effectiveness of GA to enhance landslide disaster risk management. Full article

The integration of technological advancements has significantly impacted artificial intelligence (AI), enhancing the reliability of AI model outputs. This progress has led to the widespread utilization of AI across various sectors, including automotive, robotics, healthcare, space exploration, and defense. Today, air defense operations predominantly rely on laser designation. This process is entirely dependent on the capability and experience of human operators. Considering that UAV systems can have flight durations exceeding 24 h, this process is highly prone to errors due to the human factor. Therefore, the aim of this study is to automate the laser designation process using advanced deep learning algorithms on 3D point clouds obtained from different sources, thereby eliminating operator-related errors. As different data sources, dense 3D point clouds produced with photogrammetric methods containing color information, and point clouds produced with LiDAR systems were identified. The photogrammetric point cloud data were generated from images captured by the Akinci UAV’s multi-axis gimbal camera system within the scope of this study. For the point cloud data obtained from the LiDAR system, the DublinCity LiDAR dataset was used for testing purposes. The segmentation of point cloud data utilized the PointNet++ and RandLA-Net algorithms. Distinct differences were observed between the evaluated algorithms. The RandLA-Net algorithm, relying solely on geometric features, achieved an approximate accuracy of 94%, while integrating color features significantly improved its performance, raising its accuracy to nearly 97%. Similarly, the PointNet++ algorithm, relying solely on geometric features, achieved an accuracy of approximately 94%. Notably, the model developed as a unique contribution in this study involved enriching the PointNet++ algorithm by incorporating color attributes, leading to significant improvements with an approximate accuracy of 96%. The obtained results demonstrate a notable improvement in the PointNet++ algorithm with the proposed approach. Furthermore, it was demonstrated that the methodology proposed in this study can be effectively applied directly to data generated from different sources in aerial scanning systems. Full article

Space radiation particle detection plays a crucial role in scientific research and engineering practice, especially in particle species identification. Currently, commonly used in-orbit particle identification techniques include telescope methods, electrostatic analysis time of flight (ESA × TOF), time-of-flight energy (TOF × E), and pulse shape discrimination (PSD). However, these methods usually fail to utilize the full waveform information containing rich features, and their particle identification results may be affected by the random rise and fall of particle deposition and noise interference. In this study, a low-latency and lightweight onboard FPGA real-time particle identification platform based on full waveform information was developed utilizing the superior target classification, robustness, and generalization capabilities of convolutional neural networks (CNNs). The platform constructs diversified input datasets based on the physical features of waveforms and uses Optuna and Pytorch software architectures for model training. The hardware platform is responsible for the real-time inference of waveform data and the dynamic expansion of the dataset. The platform was utilized for deep learning training and the testing of the historical waveform data of neutron and gamma rays, and the inference time of a single waveform takes 4.9 microseconds, with an accuracy rate of over 97%. The classification expectation FOM (figure-of-merit) value of this CNN model is 133, which is better than the traditional pulse shape discrimination (PSD) algorithm’s FOM value of 0.8. The development of this platform not only improves the accuracy and efficiency of space particle discrimination but also provides an advanced tool for future space environment monitoring, which is of great value for engineering applications. Full article

Accurate flight training trajectory prediction is a key task in automatic flight maneuver evaluation and flight operations quality assurance (FOQA), which is crucial for pilot training and aviation safety management. The task is extremely challenging due to the nonlinear chaos of trajectories, the unconstrained airspace maps, and the randomization of driving patterns. In this work, a deep learning model based on data-driven modern koopman operator theory and dynamical system identification is proposed. The model does not require the manual selection of dictionaries and can automatically generate augmentation functions to achieve nonlinear trajectory space mapping. The model combines stacked neural networks to create a scalable depth approximator for approximating the finite-dimensional Koopman operator. In addition, the model uses finite-dimensional operator evolution to achieve end-to-end adaptive prediction. In particular, the model can gain some physical interpretability through operator visualization and generative dictionary functions, which can be used for downstream pattern recognition and anomaly detection tasks. Experiments show that the model performs well, particularly on flight training trajectory datasets. Full article

Lunar DRO pinpoint return is the final stage of manned deep space exploration via a lunar DRO station. A re-entry capsule suffers from complicated dynamic and thermal effects during an entire flight. The optimization of the lunar DRO return trajectory exhibits strong non-linearity. To obtain a global optimal return trajectory, an entire-flight lunar DRO pinpoint return model including a Moon–Earth transfer stage and an Earth atmosphere re-entry stage is constructed. A re-entry point on the atmosphere boundary is introduced to connect these two stages. Then, an entire-flight global optimization framework for lunar DRO pinpoint return is developed. The design of the entire-flight return trajectory is simplified as the optimization of the re-entry point. Moreover, to further improve the design efficiency, a rapid landing point prediction method for the Earth re-entry is developed based on a deep neural network. This predicting network maps the re-entry point in the atmosphere and the landing point on Earth with respect to optimal control re-entry trajectories. Numerical simulations validate the optimization accuracy and efficiency of the proposed methods. The entire-flight return trajectory achieves a high accuracy of the landing point and low fuel consumption. Full article