Abstract Onboard autonomy is an essential component in enabling increasingly complex missions into deep space. In nonlinear dynamical environments, computationally efficient guidance strategies are challenging. Many traditional approaches rely on either simplifying assumptions in the dynamical model or on abundant computational resources. This research effort employs reinforcement learning, a subset of machine learning, to produce a ‘lightweight’ closed-loop controller that is potentially suitable for onboard low-thrust guidance in challenging dynamical regions of space. The results demonstrate the controller’s ability to directly guide a spacecraft despite large initial deviations and to augment a traditional targeting guidance approach. The proposed controller functions without direct knowledge of the dynamical model; direct interaction with the nonlinear equations of motion creates a flexible learning scheme that is not limited to a single force model, mission scenario, or spacecraft. The learning process leverages high-performance computing to train a closed-loop neural network controller. This controller may be employed onboard to autonomously generate low-thrust control profiles in real-time without imposing a heavy workload on a flight computer. Control feasibility is demonstrated through sample transfers between Lyapunov orbits in the Earth–Moon system. The sample low-thrust controller exhibits remarkable robustness to perturbations and generalizes effectively to nearby motion. Finally, the flexibility of the learning framework is demonstrated across a range of mission scenarios and low-thrust engine types.

    Highlights Neural networks offer a computationally efficient approach to closed-loop guidance in multi-body dynamical regimes. Reinforcement learning produces accurate controllers that are adaptable to multiple problems, and achieve nearly 100% accuracy despite large perturbations. The learning framework is applicable to multiple spacecraft and mission scenarios. A neural network controller is capable of enhancing existing guidance approaches and is potentially suitable for onboard use.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Autonomous closed-loop guidance using reinforcement learning in a low-thrust, multi-body dynamical environment


    Beteiligte:

    Erschienen in:

    Acta Astronautica ; 186 ; 1-23


    Erscheinungsdatum :

    2021-05-07


    Format / Umfang :

    23 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Adaptive Closed-Loop Maneuver Planning for Low-Thrust Spacecraft Using Reinforcement Learning

    Lafarge, Nicholas / Howell, Kathleen / Folta, David C. | TIBKAT | 2023


    Adaptive closed-loop maneuver planning for low-thrust spacecraft using reinforcement learning

    LaFarge, Nicholas B. / Howell, Kathleen C. / Folta, David C. | Elsevier | 2023


    Simple Open-Loop and Closed-Loop Guidance Strategies for Low-Thrust Spacecraft

    Huang, Rosemary / Corless, Martin / Hwang, Inseok | AIAA | 2012


    Simple Open-Loop and Closed-Loop Guidance Strategies for Low-Thrust Spacecraft

    Huang, R. / Corless, M. / Hwang, I. et al. | British Library Conference Proceedings | 2012


    Guidance for Closed-Loop Transfers using Reinforcement Learning with Application to Libration Point Orbits

    LaFarge, Nicholas B. / Miller, Daniel / Howell, Kathleen C. et al. | AIAA | 2020