Intelligent planning framework for space-ground collaborative observation tasks based on reinforcement learning

In recent years, the demand for remote sensing satellite applications has grown rapidly, with diversified observation needs from users at all levels presenting an unprecedented scale and complexity. Traditional satellite task planning methods have obvious limitations in task allocation, scheduling, and resource assignment, making it difficult to achieve efficient collaboration and precise decision-making, and failing to effectively adapt to the growing observation demands and increasing complexity. To address these challenges, there is an urgent need to develop intelligent star-ground coordinated observation task planning methods. This article proposes a satellite-ground coordinated satellite observation task intelligent planning method based on reinforcement learning. It uses neural networks to intelligently predict observation object information to generate satellite observation demands and employs neural networks through intelligent agents for smart decision-making of satellite observation tasks, automatically generating satellite observation task timelines. The satellite task planning system and the ground task planning system use the same deep learning network model. Historical data is used on the ground to train the neural network, and the trained model parameters are then uploaded to the satellite, achieving intelligent planning of satellite-ground coordinated satellite observations. An LSTM network model is adopted for predicting the longitude and latitude coordinates of observation objects. Experimental results show that the model exhibits rapidly decreasing loss values during training with good convergence performance. A framework combining reinforcement learning algorithms with MDP (Markov Decision Process) is constructed to address the smart scheduling problem of multiple observation objects. Experiments demonstrate that this method can find optimal decision paths under multiple constraints, aligning with expectations. Research indicates that this intelligent planning method integrating LSTM and MDP holds promising applications in satellite observation task planning, providing efficient solutions for practical applications.