Learning from Demonstration by Averaging Trajectories (LAT) has been implemented using a Katana robotic manipulator. LAT works in three phases: Demonstration: Repeated recording of trajectories and detection of involved objects (located at changing positions). Generalisation: Creation of a continuos behaviour model on trajectory level for each object involved. Reproduction: Fusion of the models, adapted to an arbitrary new situation where all the objects again can be located at different positions.


    Access

    Go to TIB AV-Portal


    Export, share and cite



    Title :

    Robot Learning from Demonstration by Averaging Trajectories - Pouring into the Cup


    Subtitle :

    Experiment/Model Test




    Publication date :

    2012-01-01


    Size :

    42MB, 00:05:18:20



    Type of media :

    Audio-visual


    Type of material :

    Audio-visual


    Language :

    English






    Robot learning from demonstration of force-based tasks with multiple solution trajectories

    Rozo, Leonel / Jiménez Schlegl, Pablo / Torras, Carme | BASE | 2011

    Free access

    Robot learning from demonstration of force-based tasks with multiple solution trajectories

    Rozo Castañeda, Leonel / Jimenez Schlegl, Pablo / Torras, Carme | BASE | 2011

    Free access



    Preview

    Preview Image