Animals show remarkable rich motion skills which are still far from realizable with robots. Inspired by the neural circuits which generate rhythmic motion patterns in the spinal cord of all vertebrates, one main research direction points towards the use of central pattern generators in robots. On of the key advantages of this, is that the dimensionality of the control problem is reduced. In this work we investigate this further by introducing a multi-timescale control hierarchy with at its core a hierarchy of recurrent neural networks. By means of some robot experiments, we demonstrate that this hierarchy can embed any rhythmic motor signal by imitation learning. Furthermore, the proposed hierarchy allows the tracking of several high level motion properties (e.g.: amplitude and offset), which are usually observed at a slower rate than the generated motion. Although these experiments are preliminary, the results are promising and have the potential to open the door for rich motor skills and advanced control.


    Access

    Download


    Export, share and cite



    Title :

    Towards a neural hierarchy of time scales for motor control



    Publication date :

    2012-01-01


    Remarks:

    LECTURE NOTES IN COMPUTER SCIENCE ; ISSN: 0302-9743 ; ISBN: 9783642330926



    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Towards time- and state-dependent seismic risk over urban scales

    Haas, Michael | DataCite | 2019

    Free access

    Multiple Time Scales

    Ramnath, Rudrapatna V. | AIAA | 2010


    Control of nonlinear systems with two time scales

    Shen, Zuojun / Lu, Ping | AIAA | 2001



    Time scales in vibrational systems

    Gebhardt,J. / Kassubek,F. / ABB,Ladenburg,DE | Automotive engineering | 2004