LAUSR

Multi-satellite collaborative computing has achieved task decomposition and collaborative execution through inter-satellite links (ISLs), which has significantly improved the efficiency of task execution and system responsiveness. However, existing methods focus on single-task execution and lack multi-task parallel processing capability. Most methods ignore task priorities and dependencies, leading to excessive waiting times and poor scheduling results. To address these problems, this paper proposes a task decomposition and resource mapping method based on task priorities and resource constraints. First, we introduce a graph theoretic model to represent the task dependency and priority relationships explicitly, combined with a novel algorithm for task decomposition. Meanwhile, we construct a resource allocation model based on game theory and combine it with deep reinforcement learning to achieve resource mapping in a dynamic environment. Finally, we adopt the theory of temporal logic to formalize the execution order and time constraints of tasks and solve the dynamic scheduling problem through mixed-integer nonlinear programming to ensure the optimality and real-time updating of the scheduling scheme. The experimental results demonstrate that the proposed method improves resource utilization by up to about 24% and reduces overall execution time by up to about 42.6% in large-scale scenarios.