Automatic Place Detection and Localization in Autonomous Robotics

A. Chella, I. Macaluso, Lorenzo Riano

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

    7 Citations (Scopus)

    Abstract

    This paper presents an approach for the simultaneous learning and recognition of places applied to autonomous robotics. While noteworthy results have been achieved with respect to off-line training process for appearance-based navigation, novel issues arise when recognition and learning are simultaneous and unsupervised processes. The approach adopted here uses a Gaussian mixture model estimated by a novel incremental MML-EM to model the probability distribution of features extracted by image-preprocessing. A place detector decides which features belong to which place integrating odometric information and a hidden Markov model. Tests demonstrate that the proposed system performs as well as the ones relying on batch off-line environmental learning.
    LanguageEnglish
    Title of host publicationUnknown Host Publication
    Place of PublicationLOS ALAMITOS -- USA
    Pages741-746
    Number of pages7
    Publication statusPublished - 2007
    EventIEEE/RSJ International Conference on intelligent Robots and Systems, 2007 -
    Duration: 1 Jan 2007 → …

    Conference

    ConferenceIEEE/RSJ International Conference on intelligent Robots and Systems, 2007
    Period1/01/07 → …

    Fingerprint

    Robotics
    Hidden Markov models
    Probability distributions
    Navigation
    Detectors

    Cite this

    Chella, A., Macaluso, I., & Riano, L. (2007). Automatic Place Detection and Localization in Autonomous Robotics. In Unknown Host Publication (pp. 741-746). LOS ALAMITOS -- USA.
    Chella, A. ; Macaluso, I. ; Riano, Lorenzo. / Automatic Place Detection and Localization in Autonomous Robotics. Unknown Host Publication. LOS ALAMITOS -- USA, 2007. pp. 741-746
    @inproceedings{5a4a3ebd3c92499cae631cbc369bfde2,
    title = "Automatic Place Detection and Localization in Autonomous Robotics",
    abstract = "This paper presents an approach for the simultaneous learning and recognition of places applied to autonomous robotics. While noteworthy results have been achieved with respect to off-line training process for appearance-based navigation, novel issues arise when recognition and learning are simultaneous and unsupervised processes. The approach adopted here uses a Gaussian mixture model estimated by a novel incremental MML-EM to model the probability distribution of features extracted by image-preprocessing. A place detector decides which features belong to which place integrating odometric information and a hidden Markov model. Tests demonstrate that the proposed system performs as well as the ones relying on batch off-line environmental learning.",
    author = "A. Chella and I. Macaluso and Lorenzo Riano",
    year = "2007",
    language = "English",
    pages = "741--746",
    booktitle = "Unknown Host Publication",

    }

    Chella, A, Macaluso, I & Riano, L 2007, Automatic Place Detection and Localization in Autonomous Robotics. in Unknown Host Publication. LOS ALAMITOS -- USA, pp. 741-746, IEEE/RSJ International Conference on intelligent Robots and Systems, 2007, 1/01/07.

    Automatic Place Detection and Localization in Autonomous Robotics. / Chella, A.; Macaluso, I.; Riano, Lorenzo.

    Unknown Host Publication. LOS ALAMITOS -- USA, 2007. p. 741-746.

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

    TY - GEN

    T1 - Automatic Place Detection and Localization in Autonomous Robotics

    AU - Chella, A.

    AU - Macaluso, I.

    AU - Riano, Lorenzo

    PY - 2007

    Y1 - 2007

    N2 - This paper presents an approach for the simultaneous learning and recognition of places applied to autonomous robotics. While noteworthy results have been achieved with respect to off-line training process for appearance-based navigation, novel issues arise when recognition and learning are simultaneous and unsupervised processes. The approach adopted here uses a Gaussian mixture model estimated by a novel incremental MML-EM to model the probability distribution of features extracted by image-preprocessing. A place detector decides which features belong to which place integrating odometric information and a hidden Markov model. Tests demonstrate that the proposed system performs as well as the ones relying on batch off-line environmental learning.

    AB - This paper presents an approach for the simultaneous learning and recognition of places applied to autonomous robotics. While noteworthy results have been achieved with respect to off-line training process for appearance-based navigation, novel issues arise when recognition and learning are simultaneous and unsupervised processes. The approach adopted here uses a Gaussian mixture model estimated by a novel incremental MML-EM to model the probability distribution of features extracted by image-preprocessing. A place detector decides which features belong to which place integrating odometric information and a hidden Markov model. Tests demonstrate that the proposed system performs as well as the ones relying on batch off-line environmental learning.

    M3 - Conference contribution

    SP - 741

    EP - 746

    BT - Unknown Host Publication

    CY - LOS ALAMITOS -- USA

    ER -

    Chella A, Macaluso I, Riano L. Automatic Place Detection and Localization in Autonomous Robotics. In Unknown Host Publication. LOS ALAMITOS -- USA. 2007. p. 741-746