Adaptive Depth Graph Neural Network-Based Dynamic Task Allocation for UAV-UGVs Under Complex Environments

This paper investigates dynamic task allocation (DTA) for unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) in complex urban environments using an adaptive depth graph neural network (AD-GNN) combined with biomimetic algorithms. The goal is to improve collaborative operational efficiency for UAVs and UGVs engaged in reconnaissance, combat, relay, suicide, and electronic warfare tasks. The proposed approach validates through scenarios like urban search and rescue, counterterrorism, and disaster management. AD-GNN dynamically adjusts its depth based on scenario complexity, while biomimetic algorithms optimize task allocation by emulating natural processes. Existing methods often focus on static task allocation or separate enhancement of UAV and UGV capabilities, lacking adaptability and efficiency in unpredictable urban settings. The AD-GNN model addresses these limitations by adjusting its complexity in real-time, optimizing decision-making for task allocation. The integration of biomimetic algorithms enhances robustness and flexibility, adapting to changing operational demands. Simulations using real-world geographic information system (GIS) data in extensive urban settings demonstrate significant improvements in task allocation efficiency. UAVs and UGVs achieve operational efficiencies above 85% in search and rescue operations and 90–95% in disaster management scenarios after optimization. These results highlight the model's capability to manage and allocate tasks efficiently in dynamic and unpredictable urban environments. In conclusion, this paper contributes to autonomous systems by offering an innovative solution for DTA in urban settings, showcasing the potential of integrating advanced graph neural networks with biomimetic principles to enhance UAV and UGV fleet operations in complex environments.