Joint Optimization of Coverage Path and ISCC Resource Allocation for Energy-Constrained Unmanned Aerial Vehicle

Abstract

Unmanned Aerial Vehicle (UAV)-aided Integrated Sensing, Communication, and Computation (ISCC) networks have emerged as a core component of the low-altitude network, providing an efficient mobile platform for complex tasks. In UAV coverage missions, jointly optimizing the trajectory and ISCC resources under global energy constraints and quality of service requirements is highly intractable due to the non-convex instantaneous coupling. To tackle this challenge, we propose a Topology-Aware Hierarchical Decoupling Algorithm (TAHDA). TAHDA achieves coordinated optimization by first generating a topology-optimized coverage path via a hybrid metric and subsequently regulating the flight velocity and ISCC resources in a dynamic manner. By leveraging Lagrangian dual decomposition, we derive analytical closed-form solutions for instantaneous resource allocation, ensuring rigorous integral constraint management and real-time control. Extensive experiments verify that TAHDA reduces the penalty-modified cost by up to 49.47% compared with the standard coverage path planning baseline. Furthermore, TAHDA reduces the mission makespan by 9.60% compared with the fixed-velocity strategy. It also achieves a $4.76\times $ speedup over the alternating optimization method while attaining comparable objective performance, demonstrating a favorable trade-off between solution quality and computational efficiency.