Future exploration and human missions on large planetary bodies (e.g., moon, Mars) will require advanced guidance navigation and control algorithms for the powered descent phase, which must be capable of unprecedented levels of autonomy. The advent of machine learning, and specifically reinforcement learning, has enabled new possibilities for closed-loop autonomous guidance and navigation. In this paper, image-based reinforcement meta-learning is applied to solve the lunar pinpoint powered descent and landing task with uncertain dynamic parameters and actuator failure. The agent, a deep neural network, takes real-time images and ranging observations acquired during the descent and maps them directly to thrust command (i.e., sensor-to-action policy). Training and validation of the algorithm and Monte Carlo simulations shows that the resulting closed-loop guidance policy reaches errors in the order of meters in different scenarios, even when the environment is partially observed, and the state of the spacecraft is not fully known.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Image-Based Deep Reinforcement Meta-Learning for Autonomous Lunar Landing


    Beteiligte:
    Scorsoglio, Andrea (Autor:in) / D’Ambrosio, Andrea (Autor:in) / Ghilardi, Luca (Autor:in) / Gaudet, Brian (Autor:in) / Curti, Fabio (Autor:in) / Furfaro, Roberto (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2021-07-23


    Format / Umfang :

    13 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Image-based Deep Reinforcement Meta-Learning for Autonomous Lunar Landing

    Andrea Scorsoglio / Andrea D’Ambrosio / Luca Ghilardi et al. | BASE | 2021

    Freier Zugriff

    Image-based Deep Reinforcement Learning for Autonomous Lunar Landing

    Scorsoglio, Andrea / Furfaro, Roberto / Linares, Richard et al. | AIAA | 2020


    IMAGE-BASED DEEP REINFORCEMENT LEARNING FOR AUTONOMOUS LUNAR LANDING

    Scorsoglio, Andrea / Furfaro, Roberto / Linares, Richard et al. | TIBKAT | 2020


    Deep Learning Based Real-Time Lunar Terrain Detection for Autonomous Landing Approach

    Shekhar, Kumar Sheshank / Tanti, Harsha Avinash / Datta, Abhirup | IEEE | 2023


    Towards Autonomous Lunar Resource Excavation via Deep Reinforcement Learning

    Cloud, Joseph M. / Nieves, Rolando J. / Duke, Adam K. et al. | AIAA | 2021