Learning visual landmarks for mobile robot topological navigation

Mario Mata, Jose Maria Armingol, Arturo de la Escalera

    Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

    Abstract

    Relevant progress has been done, within the Robotics field, in mechanical systems, actuators, control and planning. This fact, allows a wide application of industrial robots, where manipulator arms, Cartesian robots, etc., widely outcomes human capacity. However, the achievement of a robust and reliable autonomous mobile robot, with ability to evolve and accomplish general tasks in unconstrained environments, is still far from accomplishment. This is due, mainly, because autonomous mobile robots suffer the limitations of nowadays perception systems. A robot has to perceive its environment in order to interact (move, find and manipulate objects, etc.) with it. Perception allows making an internal representation (model) of the environment, which has to be used for moving, avoiding collision, finding its position and its way to the target, and finding objects to manipulate them. Without a sufficient environment perception, the robot simply can’t make any secure displacement or interaction, even with extremely efficient motion or planning systems. The more unstructured an environment is, the most dependent the robot is on its sensorial system. The success of industrial robotics relies on rigidly controlled and planned environments, and a total control over robot’s position in every moment. But as the environment structure degree decreases, robot capacity gets limited.
    Original languageEnglish
    Title of host publicationMachine Learning and Robot Perception
    EditorsBruno Apolloni, Ashish Ghosh, Ferda Alpaslan, Lakhmi C. Jain, Srikanta Patnaik
    Place of PublicationBerlin
    PublisherSpringer
    Pages1-55
    Number of pages55
    ISBN (Electronic)9783540324096
    ISBN (Print)9783540265498
    DOIs
    Publication statusPublished - 2005

    Publication series

    NameStudies in Computational Intelligence
    PublisherSpringer
    Volume7
    ISSN (Print)1860-949X

    Fingerprint

    Mobile robots
    Navigation
    Robots
    Robotics
    Planning
    Industrial robots
    Manipulators
    Actuators

    Keywords

    • mobile robot
    • training image
    • deformable model
    • symbolic information
    • mobile robot navigation

    Cite this

    Mata, M., Armingol, J. M., & de la Escalera, A. (2005). Learning visual landmarks for mobile robot topological navigation. In B. Apolloni, A. Ghosh, F. Alpaslan, L. C. Jain, & S. Patnaik (Eds.), Machine Learning and Robot Perception (pp. 1-55). (Studies in Computational Intelligence; Vol. 7). Berlin: Springer. https://doi.org/10.1007/11504634_1
    Mata, Mario ; Armingol, Jose Maria ; de la Escalera, Arturo. / Learning visual landmarks for mobile robot topological navigation. Machine Learning and Robot Perception. editor / Bruno Apolloni ; Ashish Ghosh ; Ferda Alpaslan ; Lakhmi C. Jain ; Srikanta Patnaik. Berlin : Springer, 2005. pp. 1-55 (Studies in Computational Intelligence).
    @inbook{76e273a6c09e401293a517c70443bfaf,
    title = "Learning visual landmarks for mobile robot topological navigation",
    abstract = "Relevant progress has been done, within the Robotics field, in mechanical systems, actuators, control and planning. This fact, allows a wide application of industrial robots, where manipulator arms, Cartesian robots, etc., widely outcomes human capacity. However, the achievement of a robust and reliable autonomous mobile robot, with ability to evolve and accomplish general tasks in unconstrained environments, is still far from accomplishment. This is due, mainly, because autonomous mobile robots suffer the limitations of nowadays perception systems. A robot has to perceive its environment in order to interact (move, find and manipulate objects, etc.) with it. Perception allows making an internal representation (model) of the environment, which has to be used for moving, avoiding collision, finding its position and its way to the target, and finding objects to manipulate them. Without a sufficient environment perception, the robot simply can’t make any secure displacement or interaction, even with extremely efficient motion or planning systems. The more unstructured an environment is, the most dependent the robot is on its sensorial system. The success of industrial robotics relies on rigidly controlled and planned environments, and a total control over robot’s position in every moment. But as the environment structure degree decreases, robot capacity gets limited.",
    keywords = "mobile robot, training image, deformable model, symbolic information, mobile robot navigation",
    author = "Mario Mata and Armingol, {Jose Maria} and {de la Escalera}, Arturo",
    year = "2005",
    doi = "10.1007/11504634_1",
    language = "English",
    isbn = "9783540265498",
    series = "Studies in Computational Intelligence",
    publisher = "Springer",
    pages = "1--55",
    editor = "Bruno Apolloni and Ashish Ghosh and Ferda Alpaslan and {C. Jain}, Lakhmi and Srikanta Patnaik",
    booktitle = "Machine Learning and Robot Perception",

    }

    Mata, M, Armingol, JM & de la Escalera, A 2005, Learning visual landmarks for mobile robot topological navigation. in B Apolloni, A Ghosh, F Alpaslan, L C. Jain & S Patnaik (eds), Machine Learning and Robot Perception. Studies in Computational Intelligence, vol. 7, Springer, Berlin, pp. 1-55. https://doi.org/10.1007/11504634_1

    Learning visual landmarks for mobile robot topological navigation. / Mata, Mario; Armingol, Jose Maria; de la Escalera, Arturo.

    Machine Learning and Robot Perception. ed. / Bruno Apolloni; Ashish Ghosh; Ferda Alpaslan; Lakhmi C. Jain; Srikanta Patnaik. Berlin : Springer, 2005. p. 1-55 (Studies in Computational Intelligence; Vol. 7).

    Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

    TY - CHAP

    T1 - Learning visual landmarks for mobile robot topological navigation

    AU - Mata, Mario

    AU - Armingol, Jose Maria

    AU - de la Escalera, Arturo

    PY - 2005

    Y1 - 2005

    N2 - Relevant progress has been done, within the Robotics field, in mechanical systems, actuators, control and planning. This fact, allows a wide application of industrial robots, where manipulator arms, Cartesian robots, etc., widely outcomes human capacity. However, the achievement of a robust and reliable autonomous mobile robot, with ability to evolve and accomplish general tasks in unconstrained environments, is still far from accomplishment. This is due, mainly, because autonomous mobile robots suffer the limitations of nowadays perception systems. A robot has to perceive its environment in order to interact (move, find and manipulate objects, etc.) with it. Perception allows making an internal representation (model) of the environment, which has to be used for moving, avoiding collision, finding its position and its way to the target, and finding objects to manipulate them. Without a sufficient environment perception, the robot simply can’t make any secure displacement or interaction, even with extremely efficient motion or planning systems. The more unstructured an environment is, the most dependent the robot is on its sensorial system. The success of industrial robotics relies on rigidly controlled and planned environments, and a total control over robot’s position in every moment. But as the environment structure degree decreases, robot capacity gets limited.

    AB - Relevant progress has been done, within the Robotics field, in mechanical systems, actuators, control and planning. This fact, allows a wide application of industrial robots, where manipulator arms, Cartesian robots, etc., widely outcomes human capacity. However, the achievement of a robust and reliable autonomous mobile robot, with ability to evolve and accomplish general tasks in unconstrained environments, is still far from accomplishment. This is due, mainly, because autonomous mobile robots suffer the limitations of nowadays perception systems. A robot has to perceive its environment in order to interact (move, find and manipulate objects, etc.) with it. Perception allows making an internal representation (model) of the environment, which has to be used for moving, avoiding collision, finding its position and its way to the target, and finding objects to manipulate them. Without a sufficient environment perception, the robot simply can’t make any secure displacement or interaction, even with extremely efficient motion or planning systems. The more unstructured an environment is, the most dependent the robot is on its sensorial system. The success of industrial robotics relies on rigidly controlled and planned environments, and a total control over robot’s position in every moment. But as the environment structure degree decreases, robot capacity gets limited.

    KW - mobile robot

    KW - training image

    KW - deformable model

    KW - symbolic information

    KW - mobile robot navigation

    U2 - 10.1007/11504634_1

    DO - 10.1007/11504634_1

    M3 - Chapter (peer-reviewed)

    SN - 9783540265498

    T3 - Studies in Computational Intelligence

    SP - 1

    EP - 55

    BT - Machine Learning and Robot Perception

    A2 - Apolloni, Bruno

    A2 - Ghosh, Ashish

    A2 - Alpaslan, Ferda

    A2 - C. Jain, Lakhmi

    A2 - Patnaik, Srikanta

    PB - Springer

    CY - Berlin

    ER -

    Mata M, Armingol JM, de la Escalera A. Learning visual landmarks for mobile robot topological navigation. In Apolloni B, Ghosh A, Alpaslan F, C. Jain L, Patnaik S, editors, Machine Learning and Robot Perception. Berlin: Springer. 2005. p. 1-55. (Studies in Computational Intelligence). https://doi.org/10.1007/11504634_1