Learning-based control scheme to deploy modular space structures

Many space activities could benefit by learning from the available on-orbit data collected during the mission. An effective improvement in control system performance and autonomy can be obtained implementing learning-based strategies, opportunely modified to adapt themselves to specific mission requirements. Growing interest is currently being addressed to in-space assembly and deploy operations worldwide. Due to the repetitive nature of space structures geometry and assembling procedure, these missions could benefit from the data collected during previous phases. In this sense, the Iterative Learning Control (ILC) appears to be a promising tool for the purpose. The proposed paper explores the possibility of its application to space deployable systems. In particular, this study focusses on the application of ILC to those foldable systems that have a repetitive modular structure, in order to track the same deployment trajectory for each module. In this scenario, the ILC can cope with the uncertainties in the model using the deploying information originated by the previous extended modules. Thus, the control system can be considered as an online supporting signal co-operating with a traditional feedback controller to achieve better deploying performance. The system is able to learn from the past experience, reducing the tracking error of the modules belonging to the successive iteration.