Automatic stimulation of experiments and learning based on prediction failure recognition

A.G. Juarez Cordova, B. Kahl, T. Henne, E. Prassler

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    98 Downloads (Pure)

    Abstract

    In this paper we focus on the task of automatically and autonomously initiating experimentation and learning based on the recognition of prediction failure. We present a mechanism that utilizes conceptual knowledge to predict the outcome of robot actions, observes their execution and indicates when discrepancies occur. We show how this mechanism was applied to a robot that learns using the paradigm of learning by experimentation, and present first results obtained from this implementation.
    Original languageEnglish
    Title of host publicationProceedings of 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan
    PublisherInstitute of Electrical and Electronics Engineers
    Pages3607-3612
    ISBN (Print)978-1-4244-2789-5
    DOIs
    Publication statusPublished - 2009
    Eventconference; 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan; 2009-05-12; 2009-05-17 -
    Duration: 12 May 200917 May 2009

    Conference

    Conferenceconference; 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan; 2009-05-12; 2009-05-17
    Period12/05/0917/05/09
    Other2009 IEEE International Conference on Robotics and Automation, Kobe, Japan

    Fingerprint

    Dive into the research topics of 'Automatic stimulation of experiments and learning based on prediction failure recognition'. Together they form a unique fingerprint.

    Cite this