• Login
    View Item 
    •   Eurographics DL Home
    • Eurographics Workshops and Symposia
    • SCA: Eurographics/SIGGRAPH Symposium on Computer Animation
    • SCA 17: Eurographics/SIGGRAPH Symposium on Computer Animation
    • View Item
    •   Eurographics DL Home
    • Eurographics Workshops and Symposia
    • SCA: Eurographics/SIGGRAPH Symposium on Computer Animation
    • SCA 17: Eurographics/SIGGRAPH Symposium on Computer Animation
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Augmenting Sampling Based Controllers with Machine Learning

    Thumbnail
    View/Open
    11-0030-rajamaki.pdf (4.722Mb)
    sca2017_final.mp4 (108.6Mb)
    Date
    2017
    Author
    Rajamäki, Joose
    Hämäläinen, Perttu
    Pay-Per-View via TIB Hannover:

    Try if this item/paper is available.

    Metadata
    Show full item record
    Abstract
    E cient learning of 3D character control still remains an open problem despite of the remarkable recent advances in the field. We propose a new algorithm that combines planning by a samplingbased model-predictive controller and learning from the planned control, which is very noisy. We combine two methods of learning: 1) immediate but imprecise nearest-neighbor learning, and 2) slower but more precise neural network learning. The nearest neighbor learning allows to rapidly latch on to new experiences whilst the neural network learns more gradually and develops a stable representation of the data. Our experiments indicate that the learners augment each other, and allow rapid discovery and re nement of complex skills such as 3D bipedal locomotion. We demonstrate this in locomotion of 1-, 2- and 4-legged 3D characters under disturbances such as heavy projectile hits and abruptly changing target direction. When augmented with the learners, the sampling based model predictive controller can produce these stable gaits in under a minute on a 4-core CPU. During training the system runs real-time or at interactive frame rates depending on the character complexity.
    BibTeX
    @inproceedings {3099564.3099579,
    booktitle = {Eurographics/ ACM SIGGRAPH Symposium on Computer Animation},
    editor = {Bernhard Thomaszewski and KangKang Yin and Rahul Narain},
    title = {{Augmenting Sampling Based Controllers with Machine Learning}},
    author = {Rajamäki, Joose and Hämäläinen, Perttu},
    year = {2017},
    publisher = {ACM},
    ISSN = {1727-5288},
    ISBN = {978-1-4503-5091-4},
    DOI = {10.1145/3099564.3099579}
    }
    URI
    http://dx.doi.org/10.1145/3099564.3099579
    https://diglib.eg.org:443/handle/10.1145/3099564-3099579
    Collections
    • SCA 17: Eurographics/SIGGRAPH Symposium on Computer Animation

    Eurographics Association copyright © 2013 - 2020 
    Send Feedback | Contact - Imprint | Data Privacy Policy | Disable Google Analytics
    Theme by @mire NV
    System hosted at  Graz University of Technology.
    TUGFhA
     

     

    Browse

    All of Eurographics DLCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    BibTeX | TOC

    Create BibTeX Create Table of Contents

    Eurographics Association copyright © 2013 - 2020 
    Send Feedback | Contact - Imprint | Data Privacy Policy | Disable Google Analytics
    Theme by @mire NV
    System hosted at  Graz University of Technology.
    TUGFhA