The invention is methods for landing rockets with precision using deep reinforcement learning for control. Embodiments of the invention are comprised of three steps. First, sensors collect data about the rocket's physical landing environment, passing information to rocket's database and processors. Second, the processors manipulate the information with a deep reinforcement learning program to produce instructions. Third, the instructions command the rocket's control system for optimal performance during landing.


    Access

    Download


    Export, share and cite



    Title :

    Precision Landing for Rockets using Deep Reinforcement Learning


    Contributors:
    HANEY BRIAN (author)

    Publication date :

    2022-07-28


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    IPC:    B64G Raumfahrt , COSMONAUTICS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Precision landing for rockets using deep reinforcement learning

    HANEY BRIAN | European Patent Office | 2023

    Free access

    SYSTEM FOR RECEIVING VERTICAL LANDING ROCKETS

    SOLOMENNIKOV OLEG | European Patent Office | 2021

    Free access

    Soil erosion by landing rockets Final report

    Alexander, J. D. / Roberds, W. M. / Scott, R. F. | NTRS | 1966


    Soil Erosion by Landing Rockets Final Report

    J. D. Alexander / W. M. Roberds / R. F. Scott | NTIS | 1966


    FUEL-EFFICIENT DEEP REINFORCEMENT LEARNING FOR PLANETARY LANDING

    Linares, Richard / Gaudet, Brian / Furfaro, Roberto | TIBKAT | 2020