In this research, reinforcement learning techniques are combined with traditional direct shooting methods to generate optimal proximal spacecraft maneuvers. Open- and closed-loop controllers, parameterized by neural networks, are developed for terminally constrained, fuel-optimal relative motion trajectories using three different thrust models. Neurocontroller performance robustness to parametric uncertainty and bounded initial conditions is assessed. This research demonstrates that neurocontrollers offer a flexible and robust alternative approach to the solution of complex controls problems in the space domain and present a promising path forward to more capable, autonomous spacecraft.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Optimal and Robust Neural Network Controllers for Proximal Spacecraft Maneuvers


    Contributors:

    Publication date :

    2019


    Size :

    90 pages


    Type of media :

    Report


    Type of material :

    No indication


    Language :

    English




    Open- and Closed-Loop Neural Network Control for Proximal Spacecraft Maneuvers

    George, Cole / Hess, Joshuah / Cobb, Richard | TIBKAT | 2019


    Optimal spacecraft rotational maneuvers

    Junkins, John L. / Turner, James D. | TIBKAT | 1986


    Robust optimal control of flexible spacecraft during slewing maneuvers

    Ebrahimi, Asghar / Moosavian, S. Ali A. / Mirshams, Mehran | Tema Archive | 2004



    Robust Optimal Maneuvers

    Wie, Bong | AIAA | 2016