Countries are increasingly interested in spacecraft surveillance and recognition which play an important role in on-orbit maintenance, space docking, and other applications. Traditional detection methods, including radar, have many restrictions, such as excessive costs and energy supply problems. For many on-orbit servicing spacecraft, image recognition is a simple but relatively accurate method for obtaining sufficient position and direction information to offer services. However, to the best of our knowledge, few practical machine-learning models focusing on the recognition of spacecraft feature components have been reported. In addition, it is difficult to find substantial on-orbit images with which to train or evaluate such a model. In this study, we first created a new dataset containing numerous artificial images of on-orbit spacecraft with labeled components. Our base images were derived from 3D Max and STK software. These images include many types of satellites and satellite postures. Considering real-world illumination conditions and imperfect camera observations, we developed a degradation algorithm that enabled us to produce thousands of artificial images of spacecraft. The feature components of the spacecraft in all images were labeled manually. We discovered that direct utilization of the DeepLab V3+ model leads to poor edge recognition. Poorly defined edges provide imprecise position or direction information and degrade the performance of on-orbit services. Thus, the edge information of the target was taken as a supervisory guide, and was used to develop the proposed Edge Auxiliary Supervision DeepLab Network (EASDN). The main idea of EASDN is to provide a new edge auxiliary loss by calculating the L2 loss between the predicted edge masks and ground-truth edge masks during training. Our extensive experiments demonstrate that our network can perform well both on our benchmark and on real on-orbit spacecraft images from the Internet. Furthermore, the device usage and processing time meet the demands of engineering applications.

This paper studies the stability control of a target towed by a space-tug via a tether in orbital transfer. The attitude of the towed target is controlled by thrust regulation at the tug with the consideration of coupling effect between the attitudes of the tug and towed target and the motion of the flexible and elastic tether. A model based control scheme is proposed where the tug and towed target are assumed as rigid bodies and the tether is approximated as a series of extensible but incompressible rods connected by spherical hinges. The governing equations of motion of the coupled rigid-flexible multibody system are derived based on the recursive dynamics algorithm. The attitude motion of the tug with the presence of tether tension disturbance is controlled by a simple PD torque controller. The attitude motion of the towed target and the elongation oscillation of the tether are stabilized simultaneously via the tether tension by regulating the thrust at the tug. The thrust control is achieved by first designing an optimal trajectory considering the system constraints based on a reference model, and then the trajectory is tracked by a robust global terminal sliding mode controller with the consideration of thrust saturation and tether slackness avoidance. Finally, numerical simulation is carried out to demonstrate the effectiveness of the proposed attitude control law based on the thrust regulation.

One of the important applications of the space tethered system is formation flying. To satisfy the requirement for interferometry of ground targets by remote-sensing satellites, a new type of tethered solar sail spacecraft has been proposed in recent research. The replacement of subsatellites of conventional tethered satellite systems with solar sail spacecraft allows for a special formation configuration in which the main satellite is in sun-synchronous orbit and the subsolar sail is in displaced orbit. If the solar sail is at the appropriate attitude, the main satellite and the solar sail spacecraft connected by metal tethers could move side by side, hence this formation system is called transverse formation. The relative baseline of this transverse formation system is perpendicular to the ground trajectory of the satellite, effectively solving the problem that the relative baseline of conventional orbital formations varies in a trigonometric cycle. Researchers on the past ignored the mass and elasticity of the tether, and considered the tether just a constraint in the model system. Since the solar sail is generally quite light compared to the other components of the system, the model inaccuracy caused by ignoring the mass of the tether on the dynamic model and control is extremely obvious. This paper investigates the relative dynamics and control of a proposed system during the deployment process with the mass of the tether. Two precise models of satellite-sail systems are established. One is based on the dumbbell model with the mass tether for the tethered satellite system, and the other is on the basis of the beads model of a tethered satellite system. The rigid one is for control design and the flexible one is for dynamic simulation. It is concluded that the length of the tether and attitude angle of the transverse formation configuration can be decoupled and controlled separately. On the basis of the models, a length rate and LQR control law is developed and the control of the deployment and retrieval process of the tethered solar sail system is investigated. Numerical simulations are performed to verify the accuracy of the conclusions.