Deep Reinforcement Learning (DRL) methods are inefficient in the initial strategy exploration process in large-scale complex scenarios. This is becoming one of the bottlenecks in their application to large-scale game adversarial scenarios. This paper proposes a Safe reinforcement learning combined with Imitation learning for Task Assignment (SITA) method for a representative red-blue game confrontation scenario. Aiming at the problem of difficult sampling of Imitation Learning (IL), this paper combines human knowledge with adversarial rules to build a knowledge rule base; We propose the Imitation Learning with the Decoupled Network (ILDN) pre-training method to solve the problem of excessive initial invalid exploration; In order to reduce invalid exploration and improve the stability in the later stages of training, we incorporate Safe Reinforcement Learning (Safe RL) method after pre-training. Finally, we verified in the digital battlefield that the SITA method has higher training efficiency and strong generalization ability in large-scale complex scenarios.

As military technology continues to evolve and the amount of situational information available on the battlefield continues to increase, data-driven deep learning methods are becoming the primary method for air target intention recognition. Deep learning is based on a large amount of high quality data; however, in the field of intention recognition, it often faces key problems such as low data volume and unbalanced datasets due to insufficient real-world scenarios. To address these problems, we propose a new method called time-series conditional generative adversarial network with improved Hausdorff distance (IH-TCGAN). The innovation of the method is mainly reflected in three aspects: (1) Use of a transverter to map real and synthetic data into the same manifold so that they have the same intrinsic dimension; (2) Addition of a restorer and a classifier in the network structure to ensure that the model can generate high-quality multiclass temporal data; (3) An improved Hausdorff distance is proposed that can measure the time order differences between multivariate time-series data and make the generated results more reasonable. We conduct experiments using two time-series datasets, evaluate the results using various performance metrics, and visualize the results using visualization techniques. The experimental results show that IH-TCGAN is able to generate synthetic data similar to the real data and has significant advantages in the generation of time series data.

Monocular vision-based pose estimation for known uncooperative space targets plays an increasingly important role in on-orbit operations. The existing state-of-the-art methods of space target pose estimation build the 2D-3D correspondences to recover the space target pose, where space target landmark regression is a key component of the methods. The 2D heatmap representation is the dominant descriptor in landmark regression. However, its quantization error grows dramatically under low-resolution input conditions, and extra post-processing is usually needed to compute the accurate 2D pixel coordinates of landmarks from heatmaps. To overcome the aforementioned problems, we propose a novel 1D landmark representation that encodes the horizontal and vertical pixel coordinates of a landmark as two independent 1D vectors. Furthermore, we also propose a space target landmark regression network to regress the locations of landmarks in the image using 1D landmark representations. Comprehensive experiments conducted on the SPEED dataset show that the proposed 1D landmark representation helps the proposed space target landmark regression network outperform existing state-of-the-art methods at various input resolutions, especially at low resolutions. Based on the 2D landmarks predicted by the proposed space target landmark regression network, the error of space target pose estimation is also smaller than existing state-of-the-art methods under all input resolution conditions.

A novel probability-based time-modulated array (prob. TMA) for sideband radiation (SR) suppression is proposed. The elements of the TMA are activated with a probability related to the desired excitation amplitude as a way to obtain a desired radiation pattern. This minimizes the power spectral density of the sideband radiation signal and enhances its randomness. In doing so, the sideband signal behaves as an artificial additive white Gaussian noise (AWGN). By analyzing the statistical model, the transmitted signal in the sidelobe region could be avoided from being received by eavesdropper, which has a great potential in the field of physical layer secure communication. The statistical properties can be used for measure the symbol error ratio (SER) metric. A set of full-wave simulations in conjunction with numerical analysis is performed to validate the theoretical predictions, proving the accuracy and reliability of the proposed system.

With the rapid development of information technology, network-centric warfare (NCW) has become the main operational style now and even in the future, and the destruction resistance of networks has become one of the most important issues in the field. Based on the complex networks theory, the command and control (C2) network is constructed, and the topology characteristics of the network are analyzed. Aiming at the deliberate attack and random attack, the destruction resistance of C2 network is analyzed and optimized. The simulation results show that the C2 network conforms to the small-world and free-scale characteristics, and it is sensitive to deliberate attack. The strategy of low-degree edge addition can be adopted, that is, by expanding the horizontal contact between the same layer of combat entities and increasing the cross-layer contact between the different layers, the destruction resistance of C2 network can be effectively enhanced. The simulation results have a certain theoretical significance for the establishment of the C2 network and the optimization of destruction resistance of C2 network.

As target splitting is not considered in the initial development of δ-generalized labeled multi-Bernoulli (δ-GLMB) filter, the scenarios where the new targets appearing conditioned on the preexisting one are not readily addressed by this filter. In view of this, we model the group target as gamma Gaussian inverse Wishart (GGIW) distribution and derive a δ-GLMB filter based on the group splitting model, in which the target splitting event is investigated. Two simplifications of the approach are presented to improve the computing efficiency, where with splitting detection, we need not to predict the splitting events of all the GGIW components in every iteration. With component combination applied in adaptive birth, a redundant modeling for a newborn target or preexisting target could be avoided. Moreover, a method for labeling performance evaluation of the algorithm is provided. Simulations demonstrate the effectiveness of the proposed approach.