Cloud-Edge Framework for Multi-Vehicle Deployment Control using Spiking Neural Networks

Recent advances have spotlighted the use of unmanned aerial vehicles (UAVs) for defense and surveillance, focusing on cooperative monitoring and exploration. However, these UAV systems face significant operational challenges due to limited computational and energy resources, affecting their endurance and effectiveness in critical missions. This study proposes a novel approach using Spiking Neural Networks (SNNs) to overcome these limitations. SNNs, inspired by the human brain's processing efficiency, offer a shift towards more autonomous and adaptive UAV systems. Leveraging SNNs, we introduce a cloud-edge computational framework aimed at optimizing barrier coverage control and enhancing UAVs' monitoring capabilities within resource constraints. This SNN-based framework marks a considerable advancement in UAV operational capabilities, enabling longer missions, better area coverage, and adaptability to environmental changes. The effectiveness in achieving optimal barrier coverage sets a new benchmark for multivehicle systems in defense applications, underscoring the potential of brain-inspired computing in military operations and paving the way for future research in autonomous defense technologies.