Flexible Workobject Localisation for CAD -Based Robotics

Mikko Sallinen, Tapio Heikkilä

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    12 Citations (Scopus)

    Abstract

    In this paper a method to locate workobjects with splined surfaces and estimate the spatial uncertainties of the estimated parameters is presented. The reference B-spline surface patch is selected from a workobject CAD- model and is defined in the form of control vertices.The process includes the hand-eye calibration of the sensor, determination of the workobject localization and surface treating, e.g. inspection.The hand-eye calibration and workobject localization are carried out using the Bayesian form estimation with sensor fusion.Use of the recursive sensor fusion method makes calibration more flexible and accurate in handling large data sets.The spatial uncertainties in the form of eigenvalues in the direction of the eigenvectors are analyzed from the error covariance matrices of the estimated parameters.
    Original languageEnglish
    Title of host publicationProceedings of SPIE Intelligent Robots and Computer Vision XIX
    Subtitle of host publicationAlgorithms, Techniques, and Active Vision
    PublisherInternational Society for Optics and Photonics SPIE
    Pages130-139
    ISBN (Print)0-8194-3862-6
    DOIs
    Publication statusPublished - 2000
    MoE publication typeA4 Article in a conference publication
    EventIntelligent Systems and Smart Manufacturing - Boston, United States
    Duration: 7 Nov 20008 Nov 2000

    Conference

    ConferenceIntelligent Systems and Smart Manufacturing
    CountryUnited States
    CityBoston
    Period7/11/008/11/00

    Fingerprint

    Computer aided design
    Robotics
    Calibration
    Sensors
    Fusion reactions
    Covariance matrix
    Eigenvalues and eigenfunctions
    Splines
    Inspection
    Uncertainty

    Keywords

    • pose estimation
    • spatial uncertainty
    • Bayesian model
    • B-spline surface patch
    • hand-eye calibration

    Cite this

    Sallinen, M., & Heikkilä, T. (2000). Flexible Workobject Localisation for CAD -Based Robotics. In Proceedings of SPIE Intelligent Robots and Computer Vision XIX: Algorithms, Techniques, and Active Vision (pp. 130-139). International Society for Optics and Photonics SPIE. https://doi.org/10.1117/12.403756
    Sallinen, Mikko ; Heikkilä, Tapio. / Flexible Workobject Localisation for CAD -Based Robotics. Proceedings of SPIE Intelligent Robots and Computer Vision XIX: Algorithms, Techniques, and Active Vision. International Society for Optics and Photonics SPIE, 2000. pp. 130-139
    @inproceedings{da3578e4e87c4abf85d732b53559cdd1,
    title = "Flexible Workobject Localisation for CAD -Based Robotics",
    abstract = "In this paper a method to locate workobjects with splined surfaces and estimate the spatial uncertainties of the estimated parameters is presented. The reference B-spline surface patch is selected from a workobject CAD- model and is defined in the form of control vertices.The process includes the hand-eye calibration of the sensor, determination of the workobject localization and surface treating, e.g. inspection.The hand-eye calibration and workobject localization are carried out using the Bayesian form estimation with sensor fusion.Use of the recursive sensor fusion method makes calibration more flexible and accurate in handling large data sets.The spatial uncertainties in the form of eigenvalues in the direction of the eigenvectors are analyzed from the error covariance matrices of the estimated parameters.",
    keywords = "pose estimation, spatial uncertainty, Bayesian model, B-spline surface patch, hand-eye calibration",
    author = "Mikko Sallinen and Tapio Heikkil{\"a}",
    note = "Project code: A9SU00755",
    year = "2000",
    doi = "10.1117/12.403756",
    language = "English",
    isbn = "0-8194-3862-6",
    pages = "130--139",
    booktitle = "Proceedings of SPIE Intelligent Robots and Computer Vision XIX",
    publisher = "International Society for Optics and Photonics SPIE",
    address = "United States",

    }

    Sallinen, M & Heikkilä, T 2000, Flexible Workobject Localisation for CAD -Based Robotics. in Proceedings of SPIE Intelligent Robots and Computer Vision XIX: Algorithms, Techniques, and Active Vision. International Society for Optics and Photonics SPIE, pp. 130-139, Intelligent Systems and Smart Manufacturing, Boston, United States, 7/11/00. https://doi.org/10.1117/12.403756

    Flexible Workobject Localisation for CAD -Based Robotics. / Sallinen, Mikko; Heikkilä, Tapio.

    Proceedings of SPIE Intelligent Robots and Computer Vision XIX: Algorithms, Techniques, and Active Vision. International Society for Optics and Photonics SPIE, 2000. p. 130-139.

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    TY - GEN

    T1 - Flexible Workobject Localisation for CAD -Based Robotics

    AU - Sallinen, Mikko

    AU - Heikkilä, Tapio

    N1 - Project code: A9SU00755

    PY - 2000

    Y1 - 2000

    N2 - In this paper a method to locate workobjects with splined surfaces and estimate the spatial uncertainties of the estimated parameters is presented. The reference B-spline surface patch is selected from a workobject CAD- model and is defined in the form of control vertices.The process includes the hand-eye calibration of the sensor, determination of the workobject localization and surface treating, e.g. inspection.The hand-eye calibration and workobject localization are carried out using the Bayesian form estimation with sensor fusion.Use of the recursive sensor fusion method makes calibration more flexible and accurate in handling large data sets.The spatial uncertainties in the form of eigenvalues in the direction of the eigenvectors are analyzed from the error covariance matrices of the estimated parameters.

    AB - In this paper a method to locate workobjects with splined surfaces and estimate the spatial uncertainties of the estimated parameters is presented. The reference B-spline surface patch is selected from a workobject CAD- model and is defined in the form of control vertices.The process includes the hand-eye calibration of the sensor, determination of the workobject localization and surface treating, e.g. inspection.The hand-eye calibration and workobject localization are carried out using the Bayesian form estimation with sensor fusion.Use of the recursive sensor fusion method makes calibration more flexible and accurate in handling large data sets.The spatial uncertainties in the form of eigenvalues in the direction of the eigenvectors are analyzed from the error covariance matrices of the estimated parameters.

    KW - pose estimation

    KW - spatial uncertainty

    KW - Bayesian model

    KW - B-spline surface patch

    KW - hand-eye calibration

    U2 - 10.1117/12.403756

    DO - 10.1117/12.403756

    M3 - Conference article in proceedings

    SN - 0-8194-3862-6

    SP - 130

    EP - 139

    BT - Proceedings of SPIE Intelligent Robots and Computer Vision XIX

    PB - International Society for Optics and Photonics SPIE

    ER -

    Sallinen M, Heikkilä T. Flexible Workobject Localisation for CAD -Based Robotics. In Proceedings of SPIE Intelligent Robots and Computer Vision XIX: Algorithms, Techniques, and Active Vision. International Society for Optics and Photonics SPIE. 2000. p. 130-139 https://doi.org/10.1117/12.403756