With the increase in UAV scale and mission diversity, trajectory planning systems faces more and more complex constraints, which are often conflicting and strongly coupled, placing higher demands on the real-time and response capabilities of the system. At the same time, conflicts and strong coupling pose challenges the autonomous decision-making capability of the system, affecting the accuracy and efficiency of the planning system in complex environments. However, recent research advances addressing these issues have not been fully summarized. An in-depth exploration of constraint handling techniques and autonomous decision-making issues will be of great significance to the development of large-scale UAV systems. Therefore, this paper aims to provide a comprehensive overview of this topic. Firstly, the functions and application scenarios of large-scale UAV trajectory planning are introduced and classified in detail according to the planning method, realization function and the presence or absence of constraints. Then, the constraint handling techniques are described in detail, focusing on the priority ranking of constraints and the principles of their fusion and transformation methods. Then, the importance of autonomous decision-making in large-scale UAV trajectory planning is described in depth, and related dynamic adjustment algorithms are introduced. Finally, the future research directions and challenges of large-scale UAV trajectory planning are outlooked, providing directions and references for future research in the fields of UAV clustering and UAV cooperative flight.

Multi-satellite imaging mission planning (MSIMP) is an important focus in the field of satellite application. MSIMP involves a variety of coupled constraints and optimization objectives, which often require extensive simulation and evaluation when solving, leading to high computational costs and slow response times for traditional algorithms. Surrogate model expensive multi-objective evolutionary algorithms (SM-EMOEAs), which are computationally efficient and converge quickly, are effective methods for the solution of MSIMP. However, the recent advances in this field have not been comprehensively summarized; therefore, this work provides a comprehensive overview of this subject. Firstly, the basic classification of MSIMP and its different fields of application are introduced, and the constraints of MSIMP are comprehensively analyzed. Secondly, the MSIMP problem is described to clarify the application scenarios of traditional optimization algorithms in MSIMP and their properties. Thirdly, the process of MSIMP and the classical expensive multi-objective evolutionary algorithms are reviewed to explore the surrogate model and the expensive multi-objective evolutionary algorithms based on MSIMP. Fourthly, improved SM-EMOEAs for MSIMP are analyzed in depth in terms of improved surrogate models, adaptive strategies, and diversity maintenance and quality assessment of the solutions. Finally, SM-EMOEAs and SM-EMOEA-based MSIMP are analyzed in terms of the existing literature, and future trends and directions are summarized.

Fine-grained recognition of ships based on remote sensing images is crucial to safeguarding maritime rights and interests and maintaining national security. Currently, with the emergence of massive high-resolution multi-modality images, the use of multi-modality images for fine-grained recognition has become a promising technology. Fine-grained recognition of multi-modality images imposes higher requirements on the dataset samples. The key to the problem is how to extract and fuse the complementary features of multi-modality images to obtain more discriminative fusion features. The attention mechanism helps the model to pinpoint the key information in the image, resulting in a significant improvement in the model’s performance. In this paper, a dataset for fine-grained recognition of ships based on visible and near-infrared multi-modality remote sensing images has been proposed first, named Dataset for Multimodal Fine-grained Recognition of Ships (DMFGRS). It includes 1,635 pairs of visible and near-infrared remote sensing images divided into 20 categories, collated from digital orthophotos model provided by commercial remote sensing satellites. DMFGRS provides two types of annotation format files, as well as segmentation mask images corresponding to the ship targets. Then, a Multimodal Information Cross-Enhancement Network (MICE-Net) fusing features of visible and near-infrared remote sensing images, has been proposed. In the network, a dual-branch feature extraction and fusion module has been designed to obtain more expressive features. The Feature Cross Enhancement Module (FCEM) achieves the fusion enhancement of the two modal features by making the channel attention and spatial attention work cross-functionally on the feature map. A benchmark is established by evaluating state-of-the-art object recognition algorithms on DMFGRS. MICE-Net conducted experiments on DMFGRS, and the precision, recall, mAP0.5 and mAP0.5:0.95 reached 87%, 77.1%, 83.8% and 63.9%, respectively. Extensive experiments demonstrate that the proposed MICE-Net has more excellent performance on DMFGRS. Built on lightweight network YOLO, the model has excellent generalizability, and thus has good potential for application in real-life scenarios.

Low Earth orbit (LEO) satellites have unique advantages in navigation because of their high signal intensity and rapid geometric changes in a short period. In order to solve the problem of constellation performance degradation after a potential failure pertaining one or more medium Earth orbit (MEO) navigation satellites, this paper designs the LEO navigation constellation and considers the task requirements of different stages of constellation deployment. Firstly, the LEO navigation constellation is designed by a non-dominated sorting genetic algorithm II (NSGA-II). The average position dilution of precision (PDOP) is 1.676, which is an improvement compared to the average PDOP offered by the four traditional GNSS. Secondly, the staged deployment of constellation takes into account the degradation of constellation performance caused by the failure of MEO navigation satellites, and the Monte Carlo method is used to analyze the case of three simultaneous satellite failures. The results show that a single satellite failure within each orbital plane and adjacent satellites with close phase separation has a great impact on the performance of the MEO navigation constellation. On this basis, a staged deployment strategy was adopted in order to balance cost, risk, and performance. The three phases deploy 66, 156, and 288 satellites, respectively; as a make-up constellation under contingencies, a navigation enhancement constellation, and an independent navigation constellation, the deployment of the staged sub-constellations meets the mission requirements. The constellation design and staged deployment method proposed in this paper can provide reference for the future study of LEO navigation constellations.

With the development of commercial space technology and the proposal of concepts such as “Black Jack”, the Space Transport Layer (STL), and the commercial space-based Internet, large-scale low-orbit satellite constellations have become a research hotspot in the aerospace field. Large-scale low-orbit satellite constellations consist of a huge number of satellites, which makes the networking control and operation management of the constellations more complicated. It also increases the difficulty of achieving the economical and efficient networking of the constellations as well as ensuring their safe and stable operation. In this study, aiming at the problem of large-scale constellation phase control in low orbit, strategies for constellation station holding were examined. First, aiming at the problem of station keeping of large-scale constellations in low orbit, the characteristics of satellite phase drift and phase keeping were analyzed, and absolute and relative station-keeping strategies were proposed. Second, a phase-holding loop control method combining semi-major axis overshoot control and passive control was proposed, and a relative phase-maintenance scheme based on a dynamic reference satellite was designed. Then, the absolute and relative station controls of different low-orbit constellations were simulated. The simulation results showed that in order for all satellites in the constellation to maintain a phase angle deviation within ±0.1° in a low-solar-activity year, about 13 days were required on average to adjust the semi-major axis of the satellites by about 71 m. The relative position control of small-scale constellations was simulated, and only four orbital maneuvers were needed to achieve the phase angle maintenance within the threshold of ±5° for all satellites in the constellation within 300 days. Finally, it was concluded that absolute control was suitable for large-scale constellation phase preservation, and relative control was more suitable for small-scale constellation phase preservation. This paper can provide a reference and suggestions for future large-scale constellation deployment and maintenance control strategies of low-orbit constellations.

With the continuous increase in the number of in-orbit satellites and the explosive growth in the demand for observation targets, satellite resource allocation and mission scheduling are faced with the problems of declining benefits and stagnant algorithm performance. This work proposes a progressive optimization mechanism and population size adaptive strategy for an improved differential evolution algorithm (POM-PSASIDEA) in large-scale multi-satellite imaging mission planning to address the above challenges. (1) MSIMPLTS based on Multi-layer Objective Optimization is constructed, and the MSIMPLTS is processed hierarchically by setting up three sub-models (superstructure, mesostructure, and understructure) to achieve a diversity of resource selection and step-by-step refinement of optimization objectives to improve the task benefits. (2) Construct the progressive optimization mechanism, which contains the allocation optimization, time window optimization, and global optimization phases, to reduce task conflicts through the progressive decision-making of the task planning scheme in stages. (3) A population size adaptive strategy for an improved differential evolution algorithm is proposed to dynamically adjust the population size according to the evolution of the population to avoid the algorithm falling into the local optimum. The experimental results show that POM-PSASIDEA has outstanding advantages over other algorithms, such as high task benefits and a high task allocation rate when solved in a shorter time.