We consider a human-in-the-loop scenario in the context of low-shot learning. Our approach was inspired by the fact that the viability of samples in novel categories cannot be sufficiently reflected by those limited observations. Some heterogeneous samples that are quite different from existing labeled novel data can inevitably emerge in the testing phase. To this end, we consider augmenting an uncertainty assessment module into low-shot learning system to account into the disturbance of those out-of-distribution (OOD) samples. Once detected, these OOD samples are passed to human beings for active labeling. Due to the discrete nature of this uncertainty assessment process, the whole Human-In-the-Loop Low-shot (HILL) learning framework is not end-to-end trainable. We hence revisited the learning system from the aspect of reinforcement learning and introduced the REINFORCE algorithm to optimize model parameters via policy gradient. The whole system gains noticeable improvements over existing low-shot learning approaches.

Spacecraft relative trajectory planning is central to many space missions like on-orbit service and debris removal. While early attempts of machine-learning-based trajectory planning have been witnessed, they still face the open problem of how to acquire sufficient training samples to conduct robust training. In this article, we have introduced a meta-learning framework to improve the adaptation ability of the planner when facing new initial conditions. To achieve this goal, we divided the training trajectories as sub-training samples and fake testing samples. Then, the meta planner is trained by repeatedly conducting a trail training-and-testing process. To this end, the gradient information of the meta learner is initially obtained on the subtraining sets and is further adjusted by looking at its testing performance on those fake testing data. Therefore, the meta planer explicitly take account of the potential testing performance into consideration and, hence, alleviate the overfitting phenomena with few training trajectories. Simulation results substantiate the effectiveness of our approach, as well as the advantages of quick adaptation to new initial conditions without overfitting.

With the rapid development of agile Earth observation satellites (AEOSs), these satellites are able to conduct more high-quality observation missions. Nevertheless, while completing these missions takes up more data transmission and electrical energy resources, it also increases the coupling within each satellite subsystem. To address this problem, we propose a reasoning-based scheduling method for an AEOS under multiple subsystem constraints. First, we defined the AEOS mission scheduling model with multi-subsystem constraints. Second, we put forward a state variable prediction method that reflects the different coupling states of a satellite after analyzing the coupling relationships between various subsystems and identifying the primary limiting coupling states for each subsystem. Third, we established the reasoning rules corresponding to the planning strategies of different coupling states of the satellite by adding two planning strategies based on the planning strategies of existing planning methods. By comparing the proposed method to three heuristic scheduling methods and a meta-heuristic scheduling method, the results show that our method has better performance in terms of scheduling results and efficiency.

The number of remote sensing satellites has increased rapidly in parallel with the advancement of space technology and the rising demand in the space industry. Consequently, the observation effectiveness evaluation of remote sensing satellites has received extensive attention. As the core content of the effectiveness evaluation, index systems are usually established and screened using qualitative or quantitative methods. They can hardly satisfy the construction principles such as completeness and independence simultaneously. To address this issue, we propose a new method for remote sensing satellite observation effectiveness evaluation that considers various principles. Firstly, a three-layer evaluation index system structure is constructed. The principle of completeness, hierarchy, and measurability of the index system is ensured by decomposition, clustering, and preliminary screening. Secondly, the principal component contribution rate is obtained through principal component analysis. Finally, we introduce a comprehensive scoring method (ICCLR) based on the combination of independence coefficient and principal component comprehensive loss rate. It realizes the screening of an index system from the index set containing correlation relationships. The validity and optimality of the proposed method are verified through experiments and analysis of three typical tasks.

A neural network-based controller is developed to enable a chaser spacecraft to approach and capture a disabled Environmental Satellite (ENVISAT). This task is conventionally tackled by framing it as an optimal control problem. However, the optimization of such a problem is computationally expensive and not suitable for onboard implementation. In this work, a learning-based approach is used to rapidly generate the control outputs of the controller based on a series of training samples. These training samples are generated by solving multiple optimal control problems with successive iterations. Then, Radial Basis Function (RBF) neural networks are designed to mimic this optimal control strategy from the generated data. Compared with a traditional controller, the neural network controller is able to generate real-time high-quality control policies by simply passing the input through the feedforward neural network.

With the development of satellite cluster technology, the earth observation capability of satellite clusters has been greatly enhanced, along with the improvement of satellite earth observation and inter-satellite data transmission ability. Nevertheless, it is difficult to coordinate satellite observation, inter-satellite data transmission, and satellite–ground data download to satisfy the constraints of satellite multi-subsystems. In this article, the multi-satellite observation-relay transmission-downloading coupling scheduling problem is described. Based on the conventional tabu search algorithm for multi-satellite earth observation, the data transmission path planning algorithm is integrated to carry out the entire coupling process of multi-satellite observation, inter-satellite data transmission, and satellite–ground data downloading. Referring to the idea of the artificial potential field method, the satellite cluster profit-state evaluation function is introduced to enhance the local search process within the tabu search framework. Moreover, in the data transmission planning algorithm, the rule-based Dijkstra data transmission path planning method is proposed based on two data transmission path planning strategies and the satellite cluster state-strategy selection rules. The simulation results show that the proposed method can realize the entire process of scheduling satellite cluster observation, relay transmission, and downloading and enhance the ability of the satellite cluster to obtain observation data. The improved Dijkstra method enhances the adaptability of the data transmission path planning method to the multi-subsystem coupled problem, and the improved local search in the tabu search method elevates the searching capability of the algorithm.