Active localization of a robot on a lattice of RFID tags by using an entropy map

Kenri Kodaka, Haruhiko Niwa, Shigeki Sugano

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

    7 Citations (Scopus)

    Abstract

    We have developed a novel way for robots to estimate their pose dynamically in an environment in which RFID tags have been arranged. We previously developed a method for localizing robots using a particle filter. Testing in a room equipped with a lattice of RFID tags at 300-mm intervals revealed that the estimation fails when the robot's RFID readers are near the center of the robot's rotation because the reader could not detect enough tags by rotating movements when the robot's positions are not suitable. We have overcome this problem by developing an active localization algorithm that generates an entropy map from the RFID arrangement information, predicts the pose using a particle filter, and attracts the robot to the target using a dynamic model, the fundamental unit of which is rotation-based angular velocity. Testing demonstrated that a robot using this algorithm and an entropy map can estimate its pose robustly without falling into a dead zone by moving only about 20 cm at most.

    Original languageEnglish
    Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
    Pages3921-3927
    Number of pages7
    DOIs
    Publication statusPublished - 2009
    Event2009 IEEE International Conference on Robotics and Automation, ICRA '09 - Kobe
    Duration: 2009 May 122009 May 17

    Other

    Other2009 IEEE International Conference on Robotics and Automation, ICRA '09
    CityKobe
    Period09/5/1209/5/17

    Fingerprint

    Radio frequency identification (RFID)
    Entropy
    Robots
    Testing
    Angular velocity
    Dynamic models

    ASJC Scopus subject areas

    • Software
    • Artificial Intelligence
    • Control and Systems Engineering
    • Electrical and Electronic Engineering

    Cite this

    Kodaka, K., Niwa, H., & Sugano, S. (2009). Active localization of a robot on a lattice of RFID tags by using an entropy map. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 3921-3927). [5152369] https://doi.org/10.1109/ROBOT.2009.5152369

    Active localization of a robot on a lattice of RFID tags by using an entropy map. / Kodaka, Kenri; Niwa, Haruhiko; Sugano, Shigeki.

    Proceedings - IEEE International Conference on Robotics and Automation. 2009. p. 3921-3927 5152369.

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

    Kodaka, K, Niwa, H & Sugano, S 2009, Active localization of a robot on a lattice of RFID tags by using an entropy map. in Proceedings - IEEE International Conference on Robotics and Automation., 5152369, pp. 3921-3927, 2009 IEEE International Conference on Robotics and Automation, ICRA '09, Kobe, 09/5/12. https://doi.org/10.1109/ROBOT.2009.5152369
    Kodaka K, Niwa H, Sugano S. Active localization of a robot on a lattice of RFID tags by using an entropy map. In Proceedings - IEEE International Conference on Robotics and Automation. 2009. p. 3921-3927. 5152369 https://doi.org/10.1109/ROBOT.2009.5152369
    Kodaka, Kenri ; Niwa, Haruhiko ; Sugano, Shigeki. / Active localization of a robot on a lattice of RFID tags by using an entropy map. Proceedings - IEEE International Conference on Robotics and Automation. 2009. pp. 3921-3927
    @inproceedings{5c57a4a8725f475b933accaafc489a48,
    title = "Active localization of a robot on a lattice of RFID tags by using an entropy map",
    abstract = "We have developed a novel way for robots to estimate their pose dynamically in an environment in which RFID tags have been arranged. We previously developed a method for localizing robots using a particle filter. Testing in a room equipped with a lattice of RFID tags at 300-mm intervals revealed that the estimation fails when the robot's RFID readers are near the center of the robot's rotation because the reader could not detect enough tags by rotating movements when the robot's positions are not suitable. We have overcome this problem by developing an active localization algorithm that generates an entropy map from the RFID arrangement information, predicts the pose using a particle filter, and attracts the robot to the target using a dynamic model, the fundamental unit of which is rotation-based angular velocity. Testing demonstrated that a robot using this algorithm and an entropy map can estimate its pose robustly without falling into a dead zone by moving only about 20 cm at most.",
    author = "Kenri Kodaka and Haruhiko Niwa and Shigeki Sugano",
    year = "2009",
    doi = "10.1109/ROBOT.2009.5152369",
    language = "English",
    isbn = "9781424427895",
    pages = "3921--3927",
    booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",

    }

    TY - GEN

    T1 - Active localization of a robot on a lattice of RFID tags by using an entropy map

    AU - Kodaka, Kenri

    AU - Niwa, Haruhiko

    AU - Sugano, Shigeki

    PY - 2009

    Y1 - 2009

    N2 - We have developed a novel way for robots to estimate their pose dynamically in an environment in which RFID tags have been arranged. We previously developed a method for localizing robots using a particle filter. Testing in a room equipped with a lattice of RFID tags at 300-mm intervals revealed that the estimation fails when the robot's RFID readers are near the center of the robot's rotation because the reader could not detect enough tags by rotating movements when the robot's positions are not suitable. We have overcome this problem by developing an active localization algorithm that generates an entropy map from the RFID arrangement information, predicts the pose using a particle filter, and attracts the robot to the target using a dynamic model, the fundamental unit of which is rotation-based angular velocity. Testing demonstrated that a robot using this algorithm and an entropy map can estimate its pose robustly without falling into a dead zone by moving only about 20 cm at most.

    AB - We have developed a novel way for robots to estimate their pose dynamically in an environment in which RFID tags have been arranged. We previously developed a method for localizing robots using a particle filter. Testing in a room equipped with a lattice of RFID tags at 300-mm intervals revealed that the estimation fails when the robot's RFID readers are near the center of the robot's rotation because the reader could not detect enough tags by rotating movements when the robot's positions are not suitable. We have overcome this problem by developing an active localization algorithm that generates an entropy map from the RFID arrangement information, predicts the pose using a particle filter, and attracts the robot to the target using a dynamic model, the fundamental unit of which is rotation-based angular velocity. Testing demonstrated that a robot using this algorithm and an entropy map can estimate its pose robustly without falling into a dead zone by moving only about 20 cm at most.

    UR - http://www.scopus.com/inward/record.url?scp=70350366587&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=70350366587&partnerID=8YFLogxK

    U2 - 10.1109/ROBOT.2009.5152369

    DO - 10.1109/ROBOT.2009.5152369

    M3 - Conference contribution

    AN - SCOPUS:70350366587

    SN - 9781424427895

    SP - 3921

    EP - 3927

    BT - Proceedings - IEEE International Conference on Robotics and Automation

    ER -