Friction from vision

A study of algorithmic and human performance with consequences for robot perception and teleoperation

Martim Brandão, Kenji Hashimoto, Atsuo Takanishi

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

    3 Citations (Scopus)

    Abstract

    Friction estimation from vision is an important problem for robot locomotion through contact. The problem is challenging due to its dependence on many factors such as material, surface conditions and contact area. In this paper we 1) conduct an analysis of image features that correlate with humans' friction judgements; and 2) compare algorithmic to human performance at the task of predicting the coefficient of friction between different surfaces and a robot's foot. The analysis is based on two new datasets which we make publicly available. One is annotated with human judgements of friction, illumination, material and texture; the other is annotated with static coefficient of friction (COF) of a robot's foot and human judgements of friction. We propose and evaluate visual friction prediction methods based on image features, material class and text mining. And finally, we make conclusions regarding the robustness to COF uncertainty which is necessary by control and planning algorithms; the low performance of humans at the task when compared to simple predictors based on material label; and the promising use of text mining to estimate friction from vision.

    Original languageEnglish
    Title of host publicationHumanoids 2016 - IEEE-RAS International Conference on Humanoid Robots
    PublisherIEEE Computer Society
    Pages428-435
    Number of pages8
    ISBN (Electronic)9781509047185
    DOIs
    Publication statusPublished - 2016 Dec 30
    Event16th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2016 - Cancun, Mexico
    Duration: 2016 Nov 152016 Nov 17

    Other

    Other16th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2016
    CountryMexico
    CityCancun
    Period16/11/1516/11/17

    Fingerprint

    Remote control
    Robots
    Friction
    Labels
    Textures
    Lighting
    Planning

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Vision and Pattern Recognition
    • Hardware and Architecture
    • Human-Computer Interaction
    • Electrical and Electronic Engineering

    Cite this

    Brandão, M., Hashimoto, K., & Takanishi, A. (2016). Friction from vision: A study of algorithmic and human performance with consequences for robot perception and teleoperation. In Humanoids 2016 - IEEE-RAS International Conference on Humanoid Robots (pp. 428-435). [7803311] IEEE Computer Society. https://doi.org/10.1109/HUMANOIDS.2016.7803311

    Friction from vision : A study of algorithmic and human performance with consequences for robot perception and teleoperation. / Brandão, Martim; Hashimoto, Kenji; Takanishi, Atsuo.

    Humanoids 2016 - IEEE-RAS International Conference on Humanoid Robots. IEEE Computer Society, 2016. p. 428-435 7803311.

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

    Brandão, M, Hashimoto, K & Takanishi, A 2016, Friction from vision: A study of algorithmic and human performance with consequences for robot perception and teleoperation. in Humanoids 2016 - IEEE-RAS International Conference on Humanoid Robots., 7803311, IEEE Computer Society, pp. 428-435, 16th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2016, Cancun, Mexico, 16/11/15. https://doi.org/10.1109/HUMANOIDS.2016.7803311
    Brandão M, Hashimoto K, Takanishi A. Friction from vision: A study of algorithmic and human performance with consequences for robot perception and teleoperation. In Humanoids 2016 - IEEE-RAS International Conference on Humanoid Robots. IEEE Computer Society. 2016. p. 428-435. 7803311 https://doi.org/10.1109/HUMANOIDS.2016.7803311
    Brandão, Martim ; Hashimoto, Kenji ; Takanishi, Atsuo. / Friction from vision : A study of algorithmic and human performance with consequences for robot perception and teleoperation. Humanoids 2016 - IEEE-RAS International Conference on Humanoid Robots. IEEE Computer Society, 2016. pp. 428-435
    @inproceedings{9c8e5a39302d4c6c8c4a7c2fef75bffe,
    title = "Friction from vision: A study of algorithmic and human performance with consequences for robot perception and teleoperation",
    abstract = "Friction estimation from vision is an important problem for robot locomotion through contact. The problem is challenging due to its dependence on many factors such as material, surface conditions and contact area. In this paper we 1) conduct an analysis of image features that correlate with humans' friction judgements; and 2) compare algorithmic to human performance at the task of predicting the coefficient of friction between different surfaces and a robot's foot. The analysis is based on two new datasets which we make publicly available. One is annotated with human judgements of friction, illumination, material and texture; the other is annotated with static coefficient of friction (COF) of a robot's foot and human judgements of friction. We propose and evaluate visual friction prediction methods based on image features, material class and text mining. And finally, we make conclusions regarding the robustness to COF uncertainty which is necessary by control and planning algorithms; the low performance of humans at the task when compared to simple predictors based on material label; and the promising use of text mining to estimate friction from vision.",
    author = "Martim Brand{\~a}o and Kenji Hashimoto and Atsuo Takanishi",
    year = "2016",
    month = "12",
    day = "30",
    doi = "10.1109/HUMANOIDS.2016.7803311",
    language = "English",
    pages = "428--435",
    booktitle = "Humanoids 2016 - IEEE-RAS International Conference on Humanoid Robots",
    publisher = "IEEE Computer Society",
    address = "United States",

    }

    TY - GEN

    T1 - Friction from vision

    T2 - A study of algorithmic and human performance with consequences for robot perception and teleoperation

    AU - Brandão, Martim

    AU - Hashimoto, Kenji

    AU - Takanishi, Atsuo

    PY - 2016/12/30

    Y1 - 2016/12/30

    N2 - Friction estimation from vision is an important problem for robot locomotion through contact. The problem is challenging due to its dependence on many factors such as material, surface conditions and contact area. In this paper we 1) conduct an analysis of image features that correlate with humans' friction judgements; and 2) compare algorithmic to human performance at the task of predicting the coefficient of friction between different surfaces and a robot's foot. The analysis is based on two new datasets which we make publicly available. One is annotated with human judgements of friction, illumination, material and texture; the other is annotated with static coefficient of friction (COF) of a robot's foot and human judgements of friction. We propose and evaluate visual friction prediction methods based on image features, material class and text mining. And finally, we make conclusions regarding the robustness to COF uncertainty which is necessary by control and planning algorithms; the low performance of humans at the task when compared to simple predictors based on material label; and the promising use of text mining to estimate friction from vision.

    AB - Friction estimation from vision is an important problem for robot locomotion through contact. The problem is challenging due to its dependence on many factors such as material, surface conditions and contact area. In this paper we 1) conduct an analysis of image features that correlate with humans' friction judgements; and 2) compare algorithmic to human performance at the task of predicting the coefficient of friction between different surfaces and a robot's foot. The analysis is based on two new datasets which we make publicly available. One is annotated with human judgements of friction, illumination, material and texture; the other is annotated with static coefficient of friction (COF) of a robot's foot and human judgements of friction. We propose and evaluate visual friction prediction methods based on image features, material class and text mining. And finally, we make conclusions regarding the robustness to COF uncertainty which is necessary by control and planning algorithms; the low performance of humans at the task when compared to simple predictors based on material label; and the promising use of text mining to estimate friction from vision.

    UR - http://www.scopus.com/inward/record.url?scp=85010208993&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85010208993&partnerID=8YFLogxK

    U2 - 10.1109/HUMANOIDS.2016.7803311

    DO - 10.1109/HUMANOIDS.2016.7803311

    M3 - Conference contribution

    SP - 428

    EP - 435

    BT - Humanoids 2016 - IEEE-RAS International Conference on Humanoid Robots

    PB - IEEE Computer Society

    ER -