Learning from demonstration (LfD) aims at robots learning skills from human-demonstrated tasks. Robots should be able to learn at all levels of abstraction. Unlike at the level of motor primitives, high-level LfD requires symbolic representations. It thus faces the classical problem of symbol grounding. Furthermore, it requires the robot to interpret human-demonstrated actions at a higher, conceptual abstraction level. We present a method, that enables a robot to recognize human-demonstrated pick-and-place task goals on an object-relational abstraction layer. The robot can reproduce the task goals in new situations using a symbolic planner. We show that in a robotic context conceptual spaces can serve as a mean for symbol grounding at an object-relational level as well as for the recognition of conceptual similarities in effects of human-demonstrated actions. The method is evaluated in experiments on a real robot.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    High-level learning from demonstration with conceptual spaces and subspace clustering


    Contributors:


    Publication date :

    2015-05-01


    Size :

    1751071 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    High-Level Learning from Demonstration

    Ertel, Wolfgang | TIB AV-Portal | 2015

    Free access

    Reweighted sparse subspace clustering

    Xu, J. / Xu, K. / Chen, K. et al. | British Library Online Contents | 2015


    A Robust Subspace Clustering Algorithm

    Peng, L. / Zhang, J. | British Library Online Contents | 2011


    Affinity Matrix Learning through Subspace Clustering for Tolling Zone Definition

    Lentzakis, Antonis F. / Seshadri, Ravi / Ben-Akiva, Moshe | IEEE | 2021


    Conceptual Design Optimization of High Altitude Airship in Concurrent Subspace Optimization

    Liang, H. / Zhu, M. / Guo, X. et al. | British Library Conference Proceedings | 2012