Techniques for an unmanned ariel vehicle (UAV) having a closed-loop controller that is gain scheduled based on a trained machine learning model. The closed-loop controller could be a PID controller. Real-time data pertaining to the motor being controlled is input to the trained machine learning model. Examples of the real-time data includes, but is not limited to, motor current, motor voltage, and an estimate of motor thrust. The trained machine learning model may also input an error term of the closed-loop controller. Tuning constants for the closed-loop controller are derived based on the prediction from the machine learning model. Gain scheduling for the closed-loop controller may thus be performed “online” while the UAV continues on its mission. Controller gain scheduling may be performed to account for changes in a payload carried by the UAV.


    Access

    Download


    Export, share and cite



    Title :

    ADAPTIVE CONTROLLER FOR UNMANNED AIRCRAFT


    Contributors:

    Publication date :

    2024-12-12


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    IPC:    B64D Ausrüstung für Flugzeuge , EQUIPMENT FOR FITTING IN OR TO AIRCRAFT / B64U / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    UNMANNED AIRCRAFT, UNMANNED AIRCRAFT FLIGHT CONTROLLER, UNMANNED AIRCRAFT FLIGHT CONTROL METHOD, AND PROGRAM

    CHRISTOPHER THOMAS RAABE / BERGSTROEM NIKLAS | European Patent Office | 2021

    Free access

    UNMANNED AIRCRAFT CONTROLLER, AND STORAGE MEDIUM

    MIYOSHI TAKASHI | European Patent Office | 2024

    Free access


    REMOTE CONTROLLER FOR LONG DISTANCE UNMANNED AIRCRAFT

    HENRI SEYDOUX / ARSENE FERRAND / NICOLAS BRULEZ | European Patent Office | 2016

    Free access

    AIRCRAFT ADAPTIVE COORDINATED CONTROLLER

    PUCHKOV ALEKSANDR MIKHAJLOVICH / SELEZNEV ANTON EVGEN EVICH / KHLOPKIN ARTEM VLADIMIROVICH et al. | European Patent Office | 2015

    Free access