Multi-unmanned systems have demonstrated significant applications across various fields under complex or extreme operating environments. In order to make such systems highly efficient and reliable, cooperative decision-making methods have been utilized as a critical technology for successful future applications. However, current multi-agent decision-making algorithms pose many challenges, including difficulties understanding human decision processes, poor time efficiency, and reduced interpretability. Thus, a real-time online collaborative decision-making model simulating human cognition is presented in this paper to solve those problems under unknown, complex, and dynamic environments. The provided model based on the Soar cognitive architecture aims to establish domain knowledge and simulate the process of human cooperation and adversarial cognition, fostering an understanding of the environment and tasks to generate real-time adversarial decisions for multi-unmanned systems. This paper devised intricate forest environments to evaluate the collaborative capabilities of agents and their proficiency in implementing various tactical strategies while assessing the effectiveness, reliability, and real-time action of the proposed model. The results reveal significant advantages for the agents in adversarial experiments, demonstrating strong capabilities in understanding the environment and collaborating effectively. Additionally, decision-making occurs in milliseconds, with time consumption decreasing as experience accumulates, mirroring the growth pattern of human decision-making.

With the advantages of long-range flight and high payload capacity, large fixed-wing UAVs are often used in anti-terrorism missions, disaster surveillance, and emergency supply delivery. In the existing research, there is little research on the 3D model design of the V-tail fixed-wing UAV and 3D flight environment modeling. The study focuses on designing a comprehensive simulation environment using Gazebo and ROS, referencing existing large fixed-wing UAVs, to design a V-tail aircraft, incorporating realistic aircraft dynamics, aerodynamics, and flight controls. Additionally, we present a simulation environment modeling approach tailored for obstacle avoidance in no-fly zones, and have created a 3D flight environment in Gazebo, generating a large-scale terrain map based on the original grayscale heightmap. This terrain map is used to simulate potential mountainous terrain threats that a fixed-wing UAV might encounter during mission execution. We have also introduced wind disturbances and other specific no-fly zones. We integrated the V-tail fixed-wing aircraft model into the 3D flight environment in Gazebo and designed PID controllers to stabilize the aircraft’s flight attitude.

The large-scale trajectory simulation serves as a fundamental basis for the mission planning of a rocket-powered vehicle swarm. However, the traditional flight trajectory calculation method for a rocket-powered vehicle, which employs strict dynamic and kinematic models, often struggles to meet the temporal requirements of mission planning. To address the challenges of timely computation and intelligent optimization, a segmented training strategy, derived from the domain knowledge of the multi-stage flight characteristics of a rocket-powered vehicle, is integrated into the deep neural network (DNN) method. A high-precision trajectory prediction model that fuses multi-DNN is proposed, which can rapidly generate high-precision trajectory data without depending on accurate dynamic models. Based on the determination of the characteristic parameters derived from rocket-powered trajectory theory, a homemade dataset is constructed through a traditional computation method and utilized to train the DNN model. Extensive and varying numerical simulations are given to substantiate the predictive accuracy, adaptability, and stability of the proposed DNN-based method, and the corresponding comparative tests further demonstrate the effectiveness of the segmented strategy. Additionally, the real-time computational capability is also confirmed by computing the simulation of generating full trajectory data.

In scenarios where multiple high-speed flight vehicles (HFVs) perform collaborative tasks on multiple targets, the reasonable allocation of vehicle resources to the designated targets is crucial for enhancing the overall mission effectiveness. In this article, a HFV-target assignment (HTA) framework that incorporates an evaluation model and an enhanced assignment algorithm is proposed for collaborative missions. The evaluation model is designed to evaluate the overall mission effectiveness considering factors such as actual trajectory, mission success rate, and target value, which are collectively represented as distance cost and act payoff. In order to quickly obtain actual trajectories of HFVs, a data-driven prediction method based on multi-scale neural network fusion is suggested. Due to the complexity of real-world mission environments and the demand for real-time responsiveness, the target assignment for large-scale HFV swarm requires rapid and efficient solutions. In this paper, the HTA optimization problem is converted into a bipartite graph optimal matching problem and an iterative generalized Kuhn-Munkres (IGKM) algorithm is proposed. Simulation results compared with particle swarm optimization and CNN-based learning method reveal that the algorithm exhibits competitive performance in terms of solution stability and computational speed in both small-scale and large-scale scenarios.