Most people are familiar with the BRIO labyrinth game and the challenge of guiding the ball through the maze. The goal of this project was to use this game to create a platform for evaluation of control algorithms. The platform was used to evaluate a few different controlling algorithms, both traditional automatic control algorithms as well as algorithms based on online incremental learning. The game was fitted with servo actuators for tilting the maze. A camera together with computer vision algorithms were used to estimate the state of the game. The evaluated controlling algorithm had the task of calculating a proper control signal, given the estimated state of the game. The evaluated learning systems used traditional control algorithms to provide initial training data. After initial training, the systems learned from their own actions and after a while they outperformed the controller used to provide initial training.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    LEAP, A Platform for Evaluation of Control Algorithms ; Labyrintbaserad plattform för algoritmutvärdering


    Beteiligte:

    Erscheinungsdatum :

    2010-01-01


    Medientyp :

    Hochschulschrift


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    SCHWIMMENDE PLATTFORM

    PRASCHL ALEXANDER / MIKATS THOMAS / PUTSCHEK MARTIN | Europäisches Patentamt | 2018

    Freier Zugriff

    Plattform NBC

    Online Contents | 2007


    Plattform C

    Online Contents | 2007


    Europaweite Plattform

    Pernsteiner, Peter | IuD Bahn | 1995


    Plattform PQ35

    Online Contents | 2007