A reinforcement learning-based approach is proposed to design the multi-impulse rendezvous trajectories in linear relative motions. For the relative motion in elliptical orbits, the relative state propagation is obtained directly from the state transition matrix. This rendezvous problem is constructed as a Markov decision process that reflects the fuel consumption, the transfer time, the relative state, and the dynamical model. An actor–critic algorithm is used to train policy for generating rendezvous maneuvers. The results of the numerical optimization (e.g., differential evolution) are adopted as the expert data set to accelerate the training process. By deploying a policy network, the multi-impulse rendezvous trajectories can be obtained on board. Moreover, the proposed approach is also applied to generate a feasible solution for many impulses (e.g., 20 impulses), which can be used as an initial value for further optimization. The numerical examples with random initial states show that the proposed method is much faster and has slightly worse performance indexes when compared with the evolutionary algorithm.

This paper presents the methods and results submitted by the winning team from Harbin Institute of Technology of the 10th China Trajectory Optimization Competition (CTOC10). The problem posed by CTOC10 requires exploring the Jupiter system using a combined spacecraft. The exploration mission consists of the detection of Jupiter’s magnetic field and an exploration of the Galilean moons. The mission is completed through three steps: problem analysis, orbital design process, and data processing. The orbital design process is mainly divided into four parts, namely, repeating ground-track orbit design, gravity-assisted orbit design, initial orbit parameter selection, and local optimization adjustment. The designed orbit is then evaluated using a heuristic optimization algorithm applied during the data processing. Finally, six full-coverage observations of Jupiter’s magnetic field are realized under the constraints of fuel and time. The final index of the submitted result is 357.8067.