Dedicated to meeting the growing demand for multi-agent collaboration in complex scenarios, this paper introduces a parameter-sharing off-policy multi-agent path planning and the following approach. Current multi-agent path planning predominantly relies on grid-based maps, whereas our proposed approach utilizes laser scan data as input, providing a closer simulation of real-world applications. In this approach, the unmanned aerial vehicle (UAV) uses the soft actor–critic (SAC) algorithm as a planner and trains its policy to converge. This policy enables end-to-end processing of laser scan data, guiding the UAV to avoid obstacles and reach the goal. At the same time, the planner incorporates paths generated by a sampling-based method as following points. The following points are continuously updated as the UAV progresses. Multi-UAV path planning tasks are facilitated, and policy convergence is accelerated through sharing experiences among agents. To address the challenge of UAVs that are initially stationary and overly cautious near the goal, a reward function is designed to encourage UAV movement. Additionally, a multi-UAV simulation environment is established to simulate real-world UAV scenarios to support training and validation of the proposed approach. The simulation results highlight the effectiveness of the presented approach in both the training process and task performance. The presented algorithm achieves an 80% success rate to guarantee that three UAVs reach the goal points.

The reconnaissance of high-value targets is prerequisite for effective operations. The recent appreciation of deep reinforcement learning (DRL) arises from its success in navigation problems, but due to the competitiveness and complexity of the military field, the applications of DRL in the military field are still unsatisfactory. In this paper, an end-to-end DRL-based intelligent reconnaissance mission planning is proposed for dual unmanned aerial vehicle (dual UAV) cooperative reconnaissance missions under high-threat and dense situations. Comprehensive consideration is given to specific mission properties and parameter requirements through the whole modelling. Firstly, the reconnaissance mission is described as a Markov decision process (MDP), and the mission planning model based on DRL is established. Secondly, the environment and UAV motion parameters are standardized to input the neural network, aiming to deduce the difficulty of algorithm convergence. According to the concrete requirements of non-reconnaissance by radars, dual-UAV cooperation and wandering reconnaissance in the mission, four reward functions with weights are designed to enhance agent understanding to the mission. To avoid sparse reward, the clip function is used to control the reward value range. Finally, considering the continuous action space of reconnaissance mission planning, the widely applicable proximal policy optimization (PPO) algorithm is used in this paper. The simulation is carried out by combining offline training and online planning. By changing the location and number of ground detection areas, from 1 to 4, the model with PPO can maintain 20% of reconnaissance proportion and a 90% mission complete rate and help the reconnaissance UAV to complete efficient path planning. It can adapt to unknown continuous high-dimensional environmental changes, is generalizable, and reflects strong intelligent planning performance.

Based on uncertainty theory, this paper studies the problem of unmanned aerial vehicle (UAV) combat mission assignment under an uncertain environment. First, considering both the target value, which is the combat mission benefit gained from attacking the target, and the unit fuel consumption of UAV as uncertain variables, an uncertain UAV combat mission assignment model is established. And according to decisions under the realization of uncertain variables, the first stage generates an initial mission allocation scheme corresponding to the realization of target value, while the second stage dynamically adjusts the scheme according to the realization of unit fuel consumption; a two-stage uncertain UAV combat mission assignment (TUCMA) model is obtained. Then, because of the difficulty of obtaining analytical solutions due to uncertainty and the complexity of solving the second stage, the TUCMA model is transformed into an expected value-effective deterministic model of the two-stage uncertain UAV combat mission assignment (ETUCMA). A modified particle swarm optimization (PSO) algorithm is designed to solve the ETUCMA model to get the expected value-effective solution of the TUCMA model. Finally, experimental simulations of multiple UAV combat task allocation scenarios demonstrate that the proposed modified PSO algorithm yields an optimal decision with maximum combat mission benefits under a maximum iteration limit, which are significantly greater benefits than those for the mission assignment achieved by the original PSO algorithm. The proposed modified PSO exhibits superior performance compared with the ant colony optimization algorithm, enabling the acquisition of an optimal allocation scheme with greater benefits. This verifies the effectiveness and superiority of the proposed model and algorithm in maximizing combat mission benefits.

Aerial situational awareness (SA) faces significant challenges due to inherent complexity involving large-scale dynamic entities and intricate spatio-temporal relationships. While deep learning advances SA for specific data modalities (static or time-series), existing approaches often lack the holistic, vision-centric perspective essential for human decision-making. To bridge this gap, we propose a unified GNN-CV framework for operational-level SA. This framework leverages mature computer vision (CV) architectures to intelligently process radar-map-like representations, addressing diverse SA tasks within a unified paradigm. Key innovations include methods for sparse entity attribute transformation graph neural networks (SET-GNNs), large-scale radar map reconstruction, integrated feature extraction, specialized two-stage pre-training, and adaptable downstream task networks. We rigorously evaluate the framework on critical operational-level tasks: aerial swarm partitioning and configuration recognition. The framework achieves an impressive end-to-end recognition accuracy exceeding 90.1%. Notably, in specialized tactical scenarios featuring small, large, and irregular flight intervals within formations, configuration recognition accuracy surpasses 85.0%. Even in the presence of significant position and heading disturbances, accuracy remains above 80.4%, with millisecond response cycles. Experimental results highlight the benefits of leveraging mature CV techniques such as image classification, object detection, and image generation, which enhance the efficacy, resilience, and coherence of intelligent situational awareness.

This paper addresses the formation assignment problem for heterogeneous UAV swarms in dynamic mission environments. A constrained optimization model is constructed in which UAV capabilities are divided into shareable and exclusive types; a neighborhood collaboration decay factor captures the locality of capability complementarity; and a Cobb–Douglas production function evaluates position-specific effectiveness under bottleneck constraints. The objective dynamically trades off deployment costs and system risks through threat-adaptive weight adjustment. To solve the model, a Hybrid Adaptive Large Neighborhood Search (HALNS) algorithm is proposed, integrating an adaptive destroy-repair mechanism, a mathematical-programming-based local search, and an incremental re-optimization strategy for rapid dynamic response. Experiments verify that HALNS attains globally optimal solutions on small-scale instances and outperforms mainstream baselines on medium-to-large problems. The collaboration mechanism raises system effectiveness by an average of 34.75% across four mission scenarios. Compared with static re-optimization, the incremental strategy improves dynamic response performance by 58.25% while reducing runtime by up to 56.7%. Sensitivity analyses confirm the robustness of key parameters. This work provides a theoretical and algorithmic foundation for intelligent UAV swarm assignment and reconfiguration.