To address low threat avoidance efficiency and poor global path adaptability in UAV path planning under threatening environments, this paper proposes a hybrid A*-Artificial Potential Field (APF) path planning method based on spatio-temporal grid optimization. First, a new global fine-grained spatio-temporal grid system is developed by integrating advantages of GeoSOT binary encoding and BeiDou grid location code subdivision rules, enabling unified modeling of complex spatio-temporal environments. Ground threat and maze scenarios are constructed for verification. Second, traditional A* and APF algorithms are improved: the A* algorithm is enhanced with threat costs, dynamic neighborhood search, and local backtrack mechanisms to address low efficiency and incompatibility with threat avoidance; the APF algorithm is optimized with a dual gravitational field collaboration mechanism and distance-parameter-based repulsive field model to overcome local minima and unreachable goals. Finally, a sliding window-driven path association model achieves seamless collaboration between global and local planning. Experimental results show the proposed method outperforms traditional algorithms in comprehensive performance, with the improved A* algorithm excelling in path length, computation time, threat value, and search nodes, and the improved APF algorithm achieving complete safe obstacle avoidance in dynamic environments. The collaborative mechanism effectively handles complex scenarios.

Unmanned aerial vehicles (UAVs) can be used in swarms to achieve multiple tasks cooperatively. Multi-UAV and multi-target cooperative task assignments are difficult. To solve the problem of unbalanced, phased, cooperative assignment between UAVs and tasks, we establish an unbalanced, phased task assignment model that considers the constraints of task execution, time, and target task execution demand. Based on an improved consensus-based bundle algorithm (CBBA), we propose a two-tier task bidding mechanism. According to dynamic changes in new tasks, we study a dynamic assignment strategy and propose a mechanism based on task continuity adjustment and time windows. Finally, a simulation experiment is used to verify the feasibility and effectiveness of the proposed allocation method in multi-UAV target assignment scenarios. The results show that the dynamic task assignment strategy can efficiently assign random new tasks as they arise.

The research on beyond visual range air combat presents several notable challenges, including numerous elements, nonlinear coupling of dynamic models, and complex changes in the dynamics of the game. Directly applying traditional algorithms to address these challenges can result in an extensive solution space, making it difficult to elucidate the dynamic process of air combat confrontation. One-versus-one (1V1) beyond visual range air combat, as the foundational level of air combat research, holds significant importance for analyzing and understanding the game confrontation process in air combat scenarios. To address these challenges, this paper focuses on 1V1 two-plane beyond visual range air combat, analyzing the air combat process and constructing an air combat decision-making model. Building upon a typical hierarchical hybrid decision-making architecture for beyond visual range air combat, the paper develops a decision-making method based on rule-driven state transition behavior in air combat games. Additionally, the evolution of the two-plane confrontation game is analyzed and studied using evolutionary game theory. Simulation results demonstrate that the proposed decision-making method exhibits strong autonomous decision-making capabilities and provides a competitive edge in two-plane beyond visual range air combat scenarios. Furthermore, it offers good interpretability and logical coherence.

In recent years, deep learning has been extensively deployed on unmanned aerial vehicles (UAVs), particularly for object detection. As the cornerstone of UAV-based object detection, deep neural networks are susceptible to adversarial attacks, with adversarial patches being a relatively straightforward method to implement. However, current research on adversarial patches, especially those targeting UAV object detection, is limited. This scarcity is notable given the complex and dynamically changing environment inherent in UAV image acquisition, which necessitates the development of more robust adversarial patches to achieve effective attacks. To address the challenge of adversarial attacks in UAV high-altitude reconnaissance, this paper presents a robust adversarial patch generation framework. Firstly, the dataset is reconstructed by considering various environmental factors that UAVs may encounter during image collection, and the influences of reflections and shadows during photography are integrated into patch training. Additionally, a nested optimization method is employed to enhance the continuity of attacks across different altitudes. Experimental results demonstrate that the adversarial patches generated by the proposed method exhibit greater robustness in complex environments and have better transferability among similar models.

Oriented object detection in optical remote sensing images (ORSIs) is a challenging task since the targets in ORSIs are displayed in an arbitrarily oriented manner and on small scales, and are densely packed. Current state-of-the-art oriented object detection models used in ORSIs primarily evolved from anchor-based and direct regression-based detection paradigms. Nevertheless, they still encounter a design difficulty from handcrafted anchor definitions and learning complexities in direct localization regression. To tackle these issues, in this paper, we proposed a novel multi-sector oriented object detection framework called MS${\mathrm{O}}^2$-Det, which quantizes the scales and orientation prediction of targets in ORSIs via an anchor-free classification-to-regression approach. Specifically, we first represented the arbitrarily oriented bounding box as four scale offsets and angles in four quadrant sectors of the corresponding Cartesian coordinate system. Then, we divided the scales and angle space into multiple discrete sectors and obtained more accurate localization information by a coarse-granularity classification to fine-grained regression strategy. In addition, to decrease the angular-sector classification loss and accelerate the network’s convergence, we designed a smooth angular-sector label (SASL) that smoothly distributes label values with a definite tolerance radius. Finally, we proposed a localization-aided detection score (LADS) to better represent the confidence of a detected box by combining the category-classification score and the sector-selection score. The proposed MS${\mathrm{O}}^2$-Det achieves state-of-the-art results on three widely used benchmarks, including the DOTA, HRSC2016, and UCAS-AOD data sets.

Deep neural network (DNN)-based object detection has been extensively implemented in Unmanned Aerial Vehicles (UAVs). However, these architectures reveal significant vulnerabilities when faced with adversarial attacks, particularly the physically realizable adversarial patches, which are highly practicable. Existing methods for generating adversarial patches are easily affected by factors such as motion blur and color distortion, leading to a decline in the attack success rate (ASR). To address these limitations, a low-frequency robust adversarial patch (LFRAP) generation framework that integrates three dimensions of color, texture, and frequency domain is proposed. Firstly, a dynamic extraction mechanism for the environmental color pool based on clustering is proposed. This mechanism not only improves the degree of environmental integration but also reduces printing losses. Secondly, mathematical modeling of the effects of Unmanned Aerial Vehicle (UAV) high-speed motion is incorporated into the patch training process. The specialized texture derived from this modeling alleviates patch blurring and the subsequent decrease in attack efficiency caused by the high-speed movement of UAVs. Finally, a frequency domain separation strategy is introduced in the generation process to optimize the frequency space distribution, thereby reducing information loss during image recapture by UAV vision systems. The experimental results show that this framework increased the environment integration rate of the generated patches by 18.9%, and the attack success rate under the condition of motion blur increased by 19.2%, which significantly outperformed conventional methods.