Agile satellites with advanced attitude maneuvering capability are the new generation of earth observation satellites (EOSs). The continuous improvement in satellite technology and decrease in launch cost have boosted the development of agile EOSs (AEOSs). To efficiently employ the increasing orbiting AEOSs, the AEOS scheduling problem (AEOSSP) aiming to maximize the entire observation profit while satisfying all complex operational constraints, has received much attention over the past 20 years. The objectives of this article are, thus, to summarize current research on AEOSSP, identify main accomplishments and highlight potential future research directions. To this end, general definitions of AEOSSP with operational constraints are described initially, followed by its three typical variations including different definitions of observation profit, multiobjective function and autonomous model. A detailed literature review from 1997–2019 is then presented in line with four different solution methods, i.e., exact method, heuristic, metaheuristic, and machine learning. Finally, we discuss a number of topics worth pursuing in the future.

In many-objective optimization problems (MaOPs), forming sound tradeoffs between convergence and diversity for the environmental selection of evolutionary algorithms is a laborious task. In particular, strengthening the selection pressure of population toward the Pareto-optimal front becomes more challenging, since the proportion of nondominated solutions in the population scales up sharply with the increase of the number of objectives. To address these issues, this paper first defines the nondominated solutions exhibiting evident tendencies toward the Pareto-optimal front as prominent solutions, using the hyperplane formed by their neighboring solutions, to further distinguish among nondominated solutions. Then, a novel environmental selection strategy is proposed with two criteria in mind: 1) if the number of nondominated solutions is larger than the population size, all the prominent solutions are first identified to strengthen the selection pressure. Subsequently, a part of the other nondominated solutions are selected to balance convergence and diversity and 2) otherwise, all the nondominated solutions are selected; then a part of the dominated solutions are selected according to the predefined reference vectors. Moreover, based on the definition of prominent solutions and the new selection strategy, we propose a hyperplane assisted evolutionary algorithm, referred here as hpaEA, for solving MaOPs. To demonstrate the performance of hpaEA, extensive experiments are conducted to compare it with five state-of-the-art many-objective evolutionary algorithms on 36 many-objective benchmark instances. The experimental results show the superiority of hpaEA which significantly outperforms the compared algorithms on 20 out of 36 benchmark instances.

We investigate a general solution based on reinforcement learning for the agile satellite scheduling problem. The core idea of this method is to determine a value function for evaluating the long-term benefit under a certain state by training from experiences, and then apply this value function to guide decisions in unknown situations. First, the process of agile satellite scheduling is modeled as a finite Markov decision process with continuous state space and discrete action space. Two subproblems of the agile Earth observation satellite scheduling problem, i.e., the sequencing problem and the timing problem are solved by the part of the agent and the environment in the model, respectively. A satisfactory solution of the timing problem can be quickly produced by a constructive heuristic algorithm. The objective function of this problem is to maximize the total reward of the entire scheduling process. Based on the above design, we demonstrate that Q-network has advantages in fitting the long-term benefit of such problems. After that, we train the Q-network by Q-learning. The experimental results show that the trained Q-network performs efficiently to cope with unknown data, and can generate high total profit in a short time. The method has good scalability and can be applied to different types of satellite scheduling problems by customizing only the constraints checking process and reward signals.