Optimization Algorithm Based on Monte Carlo Tree Search for Single Satellite Task Planning

Earth Observation Satellites (EOS) are pivotal elements within contemporary satellite constellations, serving vital roles in both defense and civilian realms. To refine the efficiency and efficacy of individual satellite observation missions, this paper presents a task planning solution rooted in the Monte Carlo Tree algorithm. An orbit prediction method considering the fourth order long-term perturbation item is proposed using orbital elements, and the constraint satisfaction model with various types of constraints is established. Aiming at a single satellite, the task planning algorithm based on the Monte Carlo tree search (MCTS) algorithm is proposed. Finally, through simulated comparisons with traditional ant colony algorithms, the viability of this proposed algorithm is affirmed in terms of both benefits and time efficiency.