This paper is devoted to model-free attitude control of rigid spacecraft in the presence of control torque saturation and external disturbances. Specifically, a model-free deep reinforcement learning (DRL) controller is proposed, which can learn continuously according to the feedback of the environment and realize the high-precision attitude control of spacecraft without repeatedly adjusting the controller parameters. Considering the continuity of state space and action space, the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm based on actor-critic architecture is adopted. Compared with the Deep Deterministic Policy Gradient (DDPG) algorithm, TD3 has better performance. TD3 obtains the optimal policy by interacting with the environment without using any prior knowledge, so the learning process is time-consuming. Aiming at this problem, the PID-Guide TD3 algorithm is proposed, which can speed up the training speed and improve the convergence precision of the TD3 algorithm. Aiming at the problem that reinforcement learning (RL) is difficult to deploy in the actual environment, the pretraining/fine-tuning method is proposed for deployment, which can not only save training time and computing resources but also achieve good results quickly. The experimental results show that DRL controller can realize high-precision attitude stabilization and attitude tracking control, with fast response speed and small overshoot. The proposed PID-Guide TD3 algorithm has faster training speed and higher stability than the TD3 algorithm.

The safe and dependable removal of large-scale space debris has been a long-standing challenge that is critical to the safety of spacecraft and astronauts. In the process of capturing and deorbiting space debris, the space manipulator must achieve extremely high control and precision. However, strong couplings, model uncertainties, and various inevitable unknown disturbances cause many difficulties in coordinated control of the space manipulator. To solve this challenge, this study examines the stabilization control of a space manipulator after capturing non-cooperative large-scale space debris and presents an adaptive integral sliding mode control (AISMC) scheme with time-delay estimation (TDE). The coupling term and lumped uncertainty are estimated by TDE technology, which eliminates the requirement of prior knowledge. Adaptive sliding mode control (ASMC) is used as desired injecting dynamics to compensate TDE errors, and a PID-type integral sliding mode surface is designed to reduce steady-state errors. The Lyapunov criterion is used to prove the global stability of the controller. Simulation results show that the controller has high tracking accuracy and strong robustness.

Satellite mission planning is the basis and top-level work of space missions and the beginning of each space mission. Therefore, the scientific research of satellite mission planning is very important. By analyzing the existing research results, we can know that the research on task planning mainly focuses on three aspects: research objects, established model, and solution algorithm. Starting from these three aspects vertically and then horizontally, this paper comprehensively discusses the theoretical basis, application, and advantages and disadvantages of related technologies in the research literature in recent years. Finally, based on the research on satellite mission planning, this paper puts forward its own views on the future development direction and research focus.

This paper investigates the application of particle swarm optimization (PSO) algorithm to plan joint trajectories of the space modular reconfigurable satellite (SMRS). SMRS changes its configuration by joint motions to complete various space missions; its movement stability is affected by joints motions because of the dynamic coupling effect in space. To improve the movement stability in reconfiguration progress, this paper establishes the optimization object equation to characterize the movement stability of SMRS in its reconfiguration process. The velocity-level and position-level kinematic models based on the proposed virtual joint coordinate system of SMRS are derived. The virtual joint coordinate system solves the problem of asymmetric joint coordinate system resulted by the asymmetric joint arrangement of SMRS. The six-order and seven-order polynomial curves are chosen to parameterize the joint trajectories and ensure the continuous position, velocity, and acceleration of joint motions. Finally, PSO algorithm is used to optimize the trajectory parameters in two cases. Consistent optimization results in terms of the six-order and seven-order polynomial in both cases prove the PSO algorithm can be effectively used for joint trajectory planning of SMRS.

Space modular self-reconfigurable satellite (SMSRS) is a new type of satellite. The research on self-collision avoidance of SMSRS is important for its on-orbit safety but is not completely solved. This paper offers a new method for joint path planning for self-collision avoidance of SMSRS. Firstly, we establish the collision detection model for SMSRS based on forward kinematics and the spherical nonholonomic envelope to detect the collision occurring in SMSRS. Then, to achieve offline path planning in joint space, we proposed the self-collision avoidance strategy, which splices multiple C-spaces based on the pre-defined joint path into a binary map, and then transforms the binary map into a map with the dangerous potential field, and planning algorithms based on a map with the dangerous potential field is proposed to find the optimal collision-free path. The new method is applied to two cases and both find collision-free joint paths for SMSRS successfully, which demonstrates the feasibility of the method. In addition, this study bridges the gap in the study of self-collision avoidance of super-redundant self-reconfigurable satellites.

Adopting appropriate protective structures to resist the impact of micrometeoroid or space debris on spacecraft is a valuable research content of space engineering. After the single-layer board and Whipple protective structure, the stuffed protective structure has become one of the research focuses in recent years. However, due to the different filling materials and filling modes, the prediction of hypervelocity impact damage of projectile by using the explicit ballistic limit equation of the stuffed protective structure will lead to some deviation between the predicted results and the measured data. In this paper, the problem is transformed into a binary classification problem, which is characterized by projectile impact parameters and protective structure parameters. And a novel method is proposed to predict the hypervelocity impact damage of the stuffed protective structure under the stacking ensemble learning framework. In this method, the hypervelocity impact damage data set of the stuffed protective structure is firstly divided into specific data subsets. Extreme Gradient Boosting (XGBoost), Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) are taken as the base models of the stacking ensemble learning framework. And each base model is trained by using the divided sub-datasets. Thus the meta-features with stronger generalization ability are extracted. Then, the Long Short Term Memory (LSTM) network is used as the meta-model of the stacking ensemble learning framework, and the meta-features extracted before are used to train it. In this way, the high-precision prediction of the impact damage of the stuffed protective structure is realized under the small data set. The experimental results show that the stacking ensemble learning model has a good prediction effect on the impact damage of the stuffed protective structure. The cross-validation under different training sample sizes further proves that the stacking ensemble learning model has excellent robustness and accuracy.