Abstract In this paper, a survey on the machine learning techniques in spacecraft control design is given. Among the applications of machine learning on the subject are the design of optimal interplanetary trajectories, the synthesis of controllers to stabilize orbital or angular motion, formation control, the design of control laws for landing on the surface of a celestial body. All the works are classified into two almost equal groups — the supervised learning (stochastic and deterministic methods) and the reinforcement learning (direct and value-based approaches). Stochastic supervised learning methods are based on stochastic optimization procedures, random initialization of neural networks weights, and stochastic nature of the obtained results. Deterministic methods are based on the Lyapunov theory; the network training is a deterministic process. The division of reinforcement learning methods into direct and value-based approaches is similar to the separation into direct and indirect methods in the optimal control theory. We discuss the main ideas, advantages, and drawbacks of the techniques and give some recommendations for future investigations. We also highlight interesting ideas and approaches in the application of machine learning methods that can be used in a broad variety of astrodynamical problems.

    Highlights Machine learning techniques in various spacecraft control applications are reviewed. The supervised learning techniques are divided into stochastic and deterministic. The reinforcement learning techniques are classified into direct and value-based. Main ideas, advantages, and drawbacks of the techniques are discussed. Recommendations for future theoretical and applied studies are given.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Survey of machine learning techniques in spacecraft control design


    Beteiligte:

    Erschienen in:

    Acta Astronautica ; 186 ; 87-97


    Erscheinungsdatum :

    2021-05-07


    Format / Umfang :

    11 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    MACHINE LEARNING TECHNIQUES FOR AUTONOMOUS SPACECRAFT GUIDANCE DURING PROXIMITY OPERATIONS

    Federici, Lorenzo / Benedikter, Boris / Zavoli, Alessandro | TIBKAT | 2021


    Machine Learning Techniques for Autonomous Spacecraft Guidance during Proximity Operations

    Federici, Lorenzo / Benedikter, Boris / Zavoli, Alessandro | AIAA | 2021


    Using experimental design techniques for spacecraft control simulation

    Gordon, S.C. / Ausink, J.A. / Berdine, R.J. | Tema Archiv | 1994


    Survey of Spacecraft Thermal Design Solutions

    R. Humphries / R. Wegrich / E. Pierce et al. | NTIS | 1991


    Modelling and Simulation of Spacecraft Hardware based on Machine Learning Techniques

    Nepal, Ayush Mani | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2019

    Freier Zugriff