Emergency evacuation is to transfer people from dangerous places to safe areas, so as to reduce or even avoid the potential harm to people. It is inherently a comprehensive system composed of evacuation managers, evacuees, road networks, shelters, etc. Security is one of the important indicators of such system. Moreover, in order to ensure the normal and efficient operation of evacuation system, each component should cooperate well with each other, thus making stability another important index of the evacuation system. In order to optimize evacuation safety, some residential areas may be arranged to stay much longer which is hard to be accepted, namely, the stability of evacuation system is low. In this paper, a system-based evacuation CSO model at residential level is proposed which compromises the security and stability of evacuation systems. The CSO model is a bi-level network optimization model, the upper level aims at minimizing the total risk of evacuation subject to the residential tolerance level and the lower level conveys a cell transmission-based dynamic traffic assignment problem. Using our model, we also study the impact of the number of shelters, the organizational form of road intersections, the uncertainty of evacuation demand and risk distribution on evacuation system.

As a crucial component in the evolution of modern warfare toward digitization and intelligentization, unmanned aerial vehicle (UAV) equipment requires a more precise and efficient operation and maintenance (O&M) system. Based on the Department of Defense Architecture Framework (DoDAF) 2.0, the integration of Multi-Agent Systems (MAS) and military simulation technology provides a comprehensive, rational, and feasible theoretical foundation for the construction and validation of an intelligent O&M system for UAV equipment. Firstly, starting from the O&M tasks of UAV equipment in intelligent warfare, this study analyzes the capability requirements for intelligent UAV O&M by following the generation path of scenarios, activities, and capabilities. Three core capabilities are proposed: situational awareness, decision support, and mission execution. Secondly, various O&M tasks are decomposed into behaviors of multiple types of agents, and based on this, an intelligent O&M system for UAV equipment is designed using a “cloud-edge-terminal” distributed architecture. Finally, simulations are conducted to model and validate UAV equipment maintenance tasks. Experimental results demonstrate that the MAS-based UAV O&M system significantly enhances support efficiency, accuracy, and response speed, offering a novel solution for O&M in future UAV operations.

To enhance path planning efficiency in unmanned aerial vehicle (UAV) search missions in complex environments, this paper proposes a coverage path planning (CPP) algorithm for a UAV that integrates the deep Q-network (DQN) with the A* algorithm (DQN-A*). In the proposed DQN-A* algorithm, a dual-driven reward mechanism is established, comprising a probability-weighted reward and a step-dependent reward, steering the UAV toward high-probability regions. Furthermore, to handle previously unknown obstacles in real time, the algorithm employs a multi-stage obstacle-identification strategy, enabling the UAV to improve coverage of traversable cells by dynamically adjusting its local path when newly detected obstacles are encountered. A theoretical analysis derives a principled recommended range for the UAV positional identifier based on statistical feature analysis; this range is then validated through extensive simulations. Additionally, Hamiltonian path pre-training is introduced to accelerate convergence. Comparative simulations demonstrate that the proposed DQN-A* algorithm achieves higher area-coverage and target-detection probabilities than benchmark algorithms in environments with unknown obstacles, offering valuable insights for positional encoding in deep reinforcement learning (DRL)-based robotic coverage problems.

To address the dynamic changes and uncertainties in complex search and rescue environments while enhancing operational efficiency, this paper proposes a coverage path planning algorithm for UAVs based on deep reinforcement learning. The algorithm incorporates the probability distribution variations of target presence across sub-regions, establishing a dual-reward mechanism comprising probability-weighted reward increments and flight-duration-dependent reward decay. This strategy prioritizes UAV exploration of high-probability target areas. Simulation experiments demonstrate that the DRL-based algorithm exhibits robust adaptability to environmental dynamics, enabling full-coverage search from arbitrary starting points. Notably, quantitative positional encoding on grid-based maps critically influences model performance, with experimental results indicating optimal efficacy when assigning values in the range of 5–10 to UAV positions under 0/1 labeling schemes for covered/uncovered regions. These findings provide critical insights into grid-based robotic path planning via deep reinforcement learning, contributing novel methodologies to the field of autonomous search systems.