This paper proposes an approach to domain transfer based on a pairwise loss function that helps transfer control policies learned in simulation onto a real robot. We explore the idea in the context of a “category level” manipulation task where a control policy is learned that enables a robot to perform a mating task involving novel objects. We explore the case where depth images are used as the main form of sensor input. Our experimental results demonstrate that proposed method consistently outperforms baseline methods that train only in simulation or that combine real and simulated data in a naive way.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Adapting Control Policies from Simulation to Reality Using a Pairwise Loss


    Additional title:

    Springer Proceedings in Advanced Robotics


    Contributors:

    Conference:

    International Symposium on Experimental Robotics ; 2018 ; Buenos Aires, Argentina November 05, 2018 - November 08, 2018



    Publication date :

    2020-01-23


    Size :

    11 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Adapting Control Policies from Simulation to Reality Using a Pairwise Loss

    Viereck, Ulrich / Peng, Xingchao / Saenko, Kate et al. | TIBKAT | 2020


    Adapting your simulation for HLA

    Yu, L.C. / Steinman, J.S. / Blank, G.E. | Tema Archive | 1998


    Skin detection using pairwise models

    Jedynak, B. / Zheng, H. / Daoudi, M. | British Library Online Contents | 2005


    Beyond pairwise clustering

    Agarwal, S. / Jongwoo Lim, / Zelnik-Manor, L. et al. | IEEE | 2005


    Pairwise face recognition

    Guo-Dong Guo, / Hong-Jiang Zhang, / Li, S.Z. | IEEE | 2001