With the rapid development of unmanned combat aerial vehicle (UCAV)-related technologies, UCAVs are playing an increasingly important role in military operations. It has become an inevitable trend in the development of future air combat battlefields that UCAVs complete air combat tasks independently to acquire air superiority. In this paper, the UCAV maneuver decision problem in continuous action space is studied based on the deep reinforcement learning strategy optimization method. The UCAV platform model of continuous action space was established. Focusing on the problem of insufficient exploration ability of Ornstein–Uhlenbeck (OU) exploration strategy in the deep deterministic policy gradient (DDPG) algorithm, a heuristic DDPG algorithm was proposed by introducing heuristic exploration strategy, and then a UCAV air combat maneuver decision method based on a heuristic DDPG algorithm is proposed. The superior performance of the algorithm is verified by comparison with different algorithms in the test environment, and the effectiveness of the decision method is verified by simulation of air combat tasks with different difficulty and attack modes.
The utilization of unmanned aerial vehicles (UAVs) as relays significantly enhances the availability of aeronautical free space optical (FSO) /radio frequency (RF) communication links. In this paper, a trajectory optimized scheme that maximizes the energy efficiency of the UAV relay is proposed. The focus of our study lies in the maximization of energy efficiency for UAVs, taking into account practical constraints in aeronautical FSO/RF communication networks, particularly the obstruction caused by moving clouds and the required data rates. Based on the cloud modeling, a feasible deployment area for UAVs that ensures line-of-sight (LOS) communication is obtained. Especially, we derive a theoretical model of propulsion energy consumption for fixed-wing UAV at variable altitudes for three-dimensional (3D) trajectory optimization. Accordingly, an energy efficient Trajectory Planning Gaining-sharing Knowledge (TPGSK) is presented to address this issue, and its effectiveness is tested. Through this algorithm, the trajectories that maximum data rate, minimum energy consumption, and optimal energy efficiency are presented, taking into consideration cloud movement. Furthermore, we find optimized energy efficiency values in various atmospheric environments. The numerical results demonstrate that the proposed design achieves significantly higher energy efficiency for the UAV-assisted hybrid FSO/RF network in comparison to other benchmark schemes
Free-space optical (FSO) communication with unmanned aerial vehicles (UAVs) as relays is a promising technology for future aeronautical communication systems. In this paper, a multiple UAV-based aeronautical communication system is proposed, wherein a hybrid FSO/radio frequency (RF) link is established to connect the Airborne Warning and Control System (AWACS) with the mobile ground station (GS). Initially, we consider the velocity variance of both AWACS and the mobile GS, along with the influence of the Doppler effect. Furthermore, four relay selection modes are proposed, and exact closed expressions are derived for the end-to-end outage probability and bit error rate (BER) of the considered system. Numerical simulations demonstrate the impact of velocity variance variation on system performance. Additionally, we analyze the applicability of these four relay modes under different platform mobility characteristics through simulation results, while discussing the optimal numbers and the deployment altitude of UAVs. Finally, effective design guidelines that can be useful for aeronautical communication system designers are presented.
3D virtual fitting based on human body contours can greatly improve the try-on effect of some tight-fitting clothes. This paper presents a fitting approach requiring merely a single RGB image and transferring clothing texture onto the human body contour, under the instruction of a UV texture guide map. DensePose is used to segment a human body into 24 patches and predict UV coordinates of each patch. 24 clothing UV patches and their textures are extracted from SURREAL dataset. Clothing patches are filtered by the patch index and the alpha value of each pixel in the patch, avoiding unnecessary replacement such as users' heads and exposed skin. They are subsequently transformed into human body corresponding patches by UV mapping. Human bodies with various figures, poses and perspectives can be fitted with clothes. Some users and clothes are tested, and satisfactory results are attained.
This paper focuses on the impact of promotional activities on the order volume of e-commerce users and the influence of unexpected events such as the COVID-19 pandemic on logistics transportation volume. The VMD algorithm is utilized to preprocess the data, and a CNN_BILSTM_RF prediction model and simulated annealing optimization model are constructed. Various software tools such as Matlab and SPSS are comprehensively employed to address the issue of freight allocation for different routes in logistics transportation. Firstly, the VMD algorithm is used to denoise the grouped data, and the CNN_BILSTcM_RF prediction model is constructed using Matlab to forecast the freight volume between DC25 and DC62, yielding conclusions such as 1774.2, 2041.5, 2718.6, 2160.9, 2251.3, and so on. Secondly, the maximum freight volume and load factor for the remaining routes after shutting down the DC5 and DC9 routes are predicted and calculated. A simulated annealing model is then applied to optimize the solution, resulting in conclusions such as 11.7288, 11.332, and so on for the overall network load. Lastly, the routes are evaluated, and the optimal transportation routes are identified as DC14-DC8, DC14-DC9, and DC36-DC4, with the addition of a new route between stations 8 and 10 to alleviate their burden, among other conclusions.