No abstract

The use of Deep Learning (DL) algorithms has improved the performance of vision-based space applications in recent years. However, generating large amounts of annotated data for training these DL algorithms has proven challenging. While synthetically generated images can be used, the DL models trained on synthetic data are often susceptible to performance degradation, when tested in real-world environments. In this context, the Interdisciplinary Center of Security, Reliability and Trust (SnT) at the University of Luxembourg has developed the 'SnT Zero-G Lab', for training and validating vision-based space algorithms in conditions emulating real-world space environments. An important aspect of the SnT Zero-G Lab development was the equipment selection. From the lessons learned during the lab development, this article presents a systematic approach combining market survey and experimental analyses for equipment selection. In particular, the article focus on the image acquisition equipment in a space lab: background materials, cameras and illumination lamps. The results from the experiment analyses show that the market survey complimented by experimental analyses is required for effective equipment selection in a space lab development project.

This paper adds on to the on-going efforts to provide more autonomy to space robots and introduces the concept of programming by demonstration or imitation learning for trajectory planning of manipulators on free-floating spacecraft. A redundant 7-DoF robotic arm is mounted on small spacecraft dedicated for debris removal, on-orbit servicing and assembly, autonomous and rendezvous docking. The motion of robot (or manipulator) arm induces reaction forces on the spacecraft and hence its attitude changes prompting the Attitude Determination and Control System (ADCS) to take large corrective action. The method introduced here is capable of finding the trajectory that minimizes the attitudinal changes thereby reducing the load on ADCS. One of the critical elements in spacecraft trajectory planning and control is the power consumption. The approach introduced in this work carry out trajectory learning offline by collecting data from demonstrations and encoding it as a probabilistic distribution of trajectories. The learned trajectory distribution can be used for planning in previously unseen situations by conditioning the probabilistic distribution. Hence almost no power is required for computations after deployment. Sampling from a conditioned distribution provides several possible trajectories from the same start to goal state. To determine the trajectory that minimizes attitudinal changes, a cost term is defined and the trajectory which minimizes this cost is considered the optimal one.

Conventional spacecraft Guidance, Navigation, and Control (GNC) architectures have been designed to receive and execute commands from ground control with minimal automation and autonomy onboard spacecraft. In contrast, Artificial Intelligence (AI)-based systems can allow real-time decision-making by considering system information that is difficult to model and incorporate in the conventional decision-making process involving ground control or human operators. With growing interests in on-orbit services with manipulation, the conventional GNC faces numerous challenges in adapting to a wide range of possible scenarios, such as removing unknown debris, potentially addressed using emerging AI-enabled robotic technologies. However, a complete paradigm shift may need years' efforts. As an intermediate solution, we introduce a novel visual GNC system with two state-of-the-art AI modules to replace the corresponding functions in the conventional GNC system for on-orbit manipulation. The AI components are as follows: (i) A Deep Learning (DL)-based pose estimation algorithm that can estimate a target's pose from two-dimensional images using a pre-trained neural network without requiring any prior information on the dynamics or state of the target. (ii) A technique for modeling and controlling space robot manipulator trajectories using probabilistic modeling and reproduction to previously unseen situations to avoid complex trajectory optimizations on board. This also minimizes the attitude disturbances of spacecraft induced on it due to the motion of the robot arm. This architecture uses a centralized camera network as the main sensor, and the trajectory learning module of the 7 degrees of freedom robotic arm is integrated into the GNC system. The intelligent visual GNC system is demonstrated by simulation of a conceptual mission—AISAT. The mission is a micro-satellite to carry out on-orbit manipulation around a non-cooperative CubeSat. The simulation shows how the GNC system works in discrete-time simulation with the control and trajectory planning are generated in Matlab/Simulink. The physics rendering engine, Eevee, renders the whole simulation to provide a graphic realism for the DL pose estimation. In the end, the testbeds developed to evaluate and demonstrate the GNC system are also introduced. The novel intelligent GNC system can be a stepping stone toward future fully autonomous orbital robot systems.

No abstract