This study investigated two distinct problems related to unknown spacecraft inertia. The first problem explored the use of a recurrent neural network to estimate spacecraft moments of inertia using angular velocity measurements. Initial results showed that, for the configuration examined, the neural network can estimate the moments of inertia when there is a known external torque. The second problem trained a reinforcement learning agent, via proximal policy optimization, to control the attitude of a spacecraft. The results demonstrated that reinforcement learning may be a viable option for guidance and control solutions where the spacecraft model may be unknown. The trained agents displayed a degree of autonomy with their ability to recover from events never experienced in training.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen


    Exportieren, teilen und zitieren



    Titel :

    Deep Reinforcement Learning Applied to Spacecraft Attitude Control and Moment of Inertia Estimation via Recurrent Neural Networks


    Beteiligte:
    N. Enders (Autor:in)

    Erscheinungsdatum :

    2021


    Format / Umfang :

    106 pages


    Medientyp :

    Report


    Format :

    Keine Angabe


    Sprache :

    Englisch




    Spacecraft Moment of Inertia Estimation Via Recurrent Neural Networks (AAS 20-483)

    Enders, Nathaniel / Curro, Joseph / Hess, Joshuah et al. | TIBKAT | 2021


    Inertia-Free Spacecraft Attitude Control with Control Moment Gyroscope Actuation

    Agarwal, K. / Weiss, A. / Kolmanovsky, I. et al. | British Library Conference Proceedings | 2012


    Inertia-Free Spacecraft Attitude Control with Control Moment Gyroscope Actuation

    Agarwal, Kshitij / Weiss, Avishai / Kolmanovsky, Ilya et al. | AIAA | 2012


    AUTONOMOUS SPACECRAFT ATTITUDE CONTROL USING DEEP REINFORCEMENT LEARNING

    Elkins, Jacob / Sood, Rohan / Rumpf, Clemens | TIBKAT | 2021


    REINFORCEMENT LEARNING FOR SPACECRAFT ATTITUDE CONTROL

    Vedant, Fnu / Allison, James / West, Matthew et al. | TIBKAT | 2020