Research

Bayesian tactile object recognition:learning and recognising objects using a new inexpensive tactile sensor


Reference:

Corradi, T., Hall, P. and Iravani, P., 2015. Bayesian tactile object recognition:learning and recognising objects using a new inexpensive tactile sensor. In: IEEE Interational Conference on Robotics and Automation (ICRA) 2015, 2015-05-26 - 2015-05-30, Washington.

Related documents:

[img]
Preview
PDF (Bayesian Tactile Object Recognition) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (1895kB) | Preview

    Abstract

    We present a Bayesian approach to tactile object recognition that improves on state-of-the-art in using single-touch events in two ways. First by improving recognition accuracy from about 90\% to about 95\%, using about half the number of touches. Second by reducing the number of touches needed for training from about 200 to about 60. In addition, we use a new tactile sensor that is less than one tenth of the cost of widely available sensors. The paper describes the sensor, the likelihood function used with the Naive Bayes classifier, and experiments on a set of ten real objects. We also provide preliminary results to test our approach for its ability to generalise to previously unencountered objects.

    Details

    Item Type Conference or Workshop Items (Paper)
    CreatorsCorradi, T., Hall, P. and Iravani, P.
    Uncontrolled Keywordstactile sensing,object recognition,bayesian,robotics
    DepartmentsFaculty of Engineering & Design > Mechanical Engineering
    Faculty of Science > Computer Science
    Research CentresMedia Technology Research Centre
    Centre for Power Transmission & Motion Control
    Centre for Sustainable Chemical Technologies
    RefereedYes
    StatusPublished
    ID Code43651

    Export

    Actions (login required)

    View Item

    Document Downloads

    More statistics for this item...