Loss of control (LOC) is a prevalent cause of drone crashes. Onboard prevention systems should be designed requiring low computing power, for which data-driven techniques provide a promising solution. This study proposes the use of recurrent neural networks (RNNs) for LOC prediction. Four architectures were trained in order to identify which RNN configuration is most suitable and if this model can predict LOC for changing aerodynamic characteristics, wind conditions, quadcopter types, and LOC events. One-hundred and seventy-two real-world LOC events were conducted using a 53 g Tiny Whoop, a 73 g URUAV UZ85, and a 265 g GEPRC CineGO quadcopter. For these flights, LOC was initiated by demanding an excessive yaw rate (2000 deg/s), which provokes an unrecoverable upset and subsequent crash. All RNNs were trained using only onboard sensor measurements. It was found that the commanded rotor values provided the clearest early warning signals for LOC because these values showed saturation before LOC. Moreover, all four architectures could correctly and reliably predict the impending LOC event 2 s before it actually occurred. Furthermore, to investigate generality of the methodology, the predictors were successfully applied to flight data in which the quadcopter mass, blade diameter, and blade count were varied.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Loss-of-Control Prediction of a Quadcopter Using Recurrent Neural Networks


    Beteiligte:

    Erschienen in:

    Erscheinungsdatum :

    2023-08-02


    Format / Umfang :

    12 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    QUADCOPTER

    KORNILOV VLADIMIR ALEKSANDROVICH / TUGAENKO VYACHESLAV YUREVICH | Europäisches Patentamt | 2020

    Freier Zugriff

    Application of artificial neural networks and NEAT algorithm to control a quadcopter

    Przychodzki, Mateusz / Niewiadomski, Artur | BASE | 2023

    Freier Zugriff

    Model Predictive Control of Quadcopter Using Physics-Guided Neural Network

    Hong, Seong Hyeon / Wang, Yi / Yu, Yang | TIBKAT | 2022


    Model Predictive Control of Quadcopter Using Physics-guided Neural Network

    Hong, Seong Hyeon / Wang, Yi / Yu, Yang | AIAA | 2022


    QUADCOPTER ARTIFICIAL INTELLIGENCE CONTROLLER AND QUADCOPTER SIMULATOR

    RESTIFO JORDAN / SKARICA VEDRAN / MILLER CHRIS | Europäisches Patentamt | 2020

    Freier Zugriff