Extrinsic dexterity through active slip control using deep predictive models

Simon Stepputtis, Yezhou Yang, Hani Ben Amor

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    We present a machine learning methodology for actively controlling slip, in order to increase robot dexterity. Leveraging recent insights in deep learning, we propose a Deep Predictive Model that uses tactile sensor information to reason about slip and its future influence on the manipulated object. The obtained information is then used to precisely manipulate objects within a robot end-effector using external perturbations imposed by gravity or acceleration. We show in a set of experiments that this approach can be used to increase a robot's repertoire of motor skills.

    Original languageEnglish (US)
    Title of host publication2018 IEEE International Conference on Robotics and Automation, ICRA 2018
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages3180-3185
    Number of pages6
    ISBN (Electronic)9781538630815
    DOIs
    StatePublished - Sep 10 2018
    Event2018 IEEE International Conference on Robotics and Automation, ICRA 2018 - Brisbane, Australia
    Duration: May 21 2018May 25 2018

    Publication series

    NameProceedings - IEEE International Conference on Robotics and Automation
    ISSN (Print)1050-4729

    Conference

    Conference2018 IEEE International Conference on Robotics and Automation, ICRA 2018
    CountryAustralia
    CityBrisbane
    Period5/21/185/25/18

    Fingerprint

    Robots
    End effectors
    Learning systems
    Gravitation
    Sensors
    Experiments
    Deep learning

    ASJC Scopus subject areas

    • Software
    • Control and Systems Engineering
    • Artificial Intelligence
    • Electrical and Electronic Engineering

    Cite this

    Stepputtis, S., Yang, Y., & Ben Amor, H. (2018). Extrinsic dexterity through active slip control using deep predictive models. In 2018 IEEE International Conference on Robotics and Automation, ICRA 2018 (pp. 3180-3185). [8461055] (Proceedings - IEEE International Conference on Robotics and Automation). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRA.2018.8461055

    Extrinsic dexterity through active slip control using deep predictive models. / Stepputtis, Simon; Yang, Yezhou; Ben Amor, Hani.

    2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 3180-3185 8461055 (Proceedings - IEEE International Conference on Robotics and Automation).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Stepputtis, S, Yang, Y & Ben Amor, H 2018, Extrinsic dexterity through active slip control using deep predictive models. in 2018 IEEE International Conference on Robotics and Automation, ICRA 2018., 8461055, Proceedings - IEEE International Conference on Robotics and Automation, Institute of Electrical and Electronics Engineers Inc., pp. 3180-3185, 2018 IEEE International Conference on Robotics and Automation, ICRA 2018, Brisbane, Australia, 5/21/18. https://doi.org/10.1109/ICRA.2018.8461055
    Stepputtis S, Yang Y, Ben Amor H. Extrinsic dexterity through active slip control using deep predictive models. In 2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 3180-3185. 8461055. (Proceedings - IEEE International Conference on Robotics and Automation). https://doi.org/10.1109/ICRA.2018.8461055
    Stepputtis, Simon ; Yang, Yezhou ; Ben Amor, Hani. / Extrinsic dexterity through active slip control using deep predictive models. 2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 3180-3185 (Proceedings - IEEE International Conference on Robotics and Automation).
    @inproceedings{f665c61505614018bc6a2cb158143843,
    title = "Extrinsic dexterity through active slip control using deep predictive models",
    abstract = "We present a machine learning methodology for actively controlling slip, in order to increase robot dexterity. Leveraging recent insights in deep learning, we propose a Deep Predictive Model that uses tactile sensor information to reason about slip and its future influence on the manipulated object. The obtained information is then used to precisely manipulate objects within a robot end-effector using external perturbations imposed by gravity or acceleration. We show in a set of experiments that this approach can be used to increase a robot's repertoire of motor skills.",
    author = "Simon Stepputtis and Yezhou Yang and {Ben Amor}, Hani",
    year = "2018",
    month = "9",
    day = "10",
    doi = "10.1109/ICRA.2018.8461055",
    language = "English (US)",
    series = "Proceedings - IEEE International Conference on Robotics and Automation",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    pages = "3180--3185",
    booktitle = "2018 IEEE International Conference on Robotics and Automation, ICRA 2018",

    }

    TY - GEN

    T1 - Extrinsic dexterity through active slip control using deep predictive models

    AU - Stepputtis, Simon

    AU - Yang, Yezhou

    AU - Ben Amor, Hani

    PY - 2018/9/10

    Y1 - 2018/9/10

    N2 - We present a machine learning methodology for actively controlling slip, in order to increase robot dexterity. Leveraging recent insights in deep learning, we propose a Deep Predictive Model that uses tactile sensor information to reason about slip and its future influence on the manipulated object. The obtained information is then used to precisely manipulate objects within a robot end-effector using external perturbations imposed by gravity or acceleration. We show in a set of experiments that this approach can be used to increase a robot's repertoire of motor skills.

    AB - We present a machine learning methodology for actively controlling slip, in order to increase robot dexterity. Leveraging recent insights in deep learning, we propose a Deep Predictive Model that uses tactile sensor information to reason about slip and its future influence on the manipulated object. The obtained information is then used to precisely manipulate objects within a robot end-effector using external perturbations imposed by gravity or acceleration. We show in a set of experiments that this approach can be used to increase a robot's repertoire of motor skills.

    UR - http://www.scopus.com/inward/record.url?scp=85063146994&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85063146994&partnerID=8YFLogxK

    U2 - 10.1109/ICRA.2018.8461055

    DO - 10.1109/ICRA.2018.8461055

    M3 - Conference contribution

    T3 - Proceedings - IEEE International Conference on Robotics and Automation

    SP - 3180

    EP - 3185

    BT - 2018 IEEE International Conference on Robotics and Automation, ICRA 2018

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -