GPS/INS integration utilizing dynamic neural networks for vehicular navigation

Aboelmagd Noureldin, Ahmed El-Shafie, Mohamed Bayoumi

    Research output: Contribution to journalArticle

    125 Citations (Scopus)

    Abstract

    Recently, methods based on Artificial Intelligence (AI) have been suggested to provide reliable positioning information for different land vehicle navigation applications integrating the Global Positioning System (GPS) with the Inertial Navigation System (INS). All existing AI-based methods are based on relating the INS error to the corresponding INS output at certain time instants and do not consider the dependence of the error on the past values of INS. This study, therefore, suggests the use of Input-Delayed Neural Networks (IDNN) to model both the INS position and velocity errors based on current and some past samples of INS position and velocity, respectively. This results in a more reliable positioning solution during long GPS outages. The proposed method is evaluated using road test data of different trajectories while both navigational and tactical grade INS are mounted inside land vehicles and integrated with GPS receivers. The performance of the IDNN - based model is also compared to both conventional (based mainly on Kalman filtering) and recently published AI - based techniques. The results showed significant improvement in positioning accuracy especially for cases of tactical grade INS and long GPS outages.

    Original languageEnglish
    Pages (from-to)48-57
    Number of pages10
    JournalInformation Fusion
    Volume12
    Issue number1
    DOIs
    Publication statusPublished - Jan 2011

    Fingerprint

    Inertial navigation systems
    Global positioning system
    Navigation
    Neural networks
    Artificial intelligence
    Outages
    Trajectories

    Keywords

    • Data fusion
    • Dynamic neural network
    • GPS
    • Inertial Navigation System (INS)
    • INS/GPS road tests

    ASJC Scopus subject areas

    • Signal Processing
    • Software
    • Hardware and Architecture
    • Information Systems

    Cite this

    GPS/INS integration utilizing dynamic neural networks for vehicular navigation. / Noureldin, Aboelmagd; El-Shafie, Ahmed; Bayoumi, Mohamed.

    In: Information Fusion, Vol. 12, No. 1, 01.2011, p. 48-57.

    Research output: Contribution to journalArticle

    Noureldin, Aboelmagd ; El-Shafie, Ahmed ; Bayoumi, Mohamed. / GPS/INS integration utilizing dynamic neural networks for vehicular navigation. In: Information Fusion. 2011 ; Vol. 12, No. 1. pp. 48-57.
    @article{29bf5cd351ed497687631e0bbd521555,
    title = "GPS/INS integration utilizing dynamic neural networks for vehicular navigation",
    abstract = "Recently, methods based on Artificial Intelligence (AI) have been suggested to provide reliable positioning information for different land vehicle navigation applications integrating the Global Positioning System (GPS) with the Inertial Navigation System (INS). All existing AI-based methods are based on relating the INS error to the corresponding INS output at certain time instants and do not consider the dependence of the error on the past values of INS. This study, therefore, suggests the use of Input-Delayed Neural Networks (IDNN) to model both the INS position and velocity errors based on current and some past samples of INS position and velocity, respectively. This results in a more reliable positioning solution during long GPS outages. The proposed method is evaluated using road test data of different trajectories while both navigational and tactical grade INS are mounted inside land vehicles and integrated with GPS receivers. The performance of the IDNN - based model is also compared to both conventional (based mainly on Kalman filtering) and recently published AI - based techniques. The results showed significant improvement in positioning accuracy especially for cases of tactical grade INS and long GPS outages.",
    keywords = "Data fusion, Dynamic neural network, GPS, Inertial Navigation System (INS), INS/GPS road tests",
    author = "Aboelmagd Noureldin and Ahmed El-Shafie and Mohamed Bayoumi",
    year = "2011",
    month = "1",
    doi = "10.1016/j.inffus.2010.01.003",
    language = "English",
    volume = "12",
    pages = "48--57",
    journal = "Information Fusion",
    issn = "1566-2535",
    publisher = "Elsevier",
    number = "1",

    }

    TY - JOUR

    T1 - GPS/INS integration utilizing dynamic neural networks for vehicular navigation

    AU - Noureldin, Aboelmagd

    AU - El-Shafie, Ahmed

    AU - Bayoumi, Mohamed

    PY - 2011/1

    Y1 - 2011/1

    N2 - Recently, methods based on Artificial Intelligence (AI) have been suggested to provide reliable positioning information for different land vehicle navigation applications integrating the Global Positioning System (GPS) with the Inertial Navigation System (INS). All existing AI-based methods are based on relating the INS error to the corresponding INS output at certain time instants and do not consider the dependence of the error on the past values of INS. This study, therefore, suggests the use of Input-Delayed Neural Networks (IDNN) to model both the INS position and velocity errors based on current and some past samples of INS position and velocity, respectively. This results in a more reliable positioning solution during long GPS outages. The proposed method is evaluated using road test data of different trajectories while both navigational and tactical grade INS are mounted inside land vehicles and integrated with GPS receivers. The performance of the IDNN - based model is also compared to both conventional (based mainly on Kalman filtering) and recently published AI - based techniques. The results showed significant improvement in positioning accuracy especially for cases of tactical grade INS and long GPS outages.

    AB - Recently, methods based on Artificial Intelligence (AI) have been suggested to provide reliable positioning information for different land vehicle navigation applications integrating the Global Positioning System (GPS) with the Inertial Navigation System (INS). All existing AI-based methods are based on relating the INS error to the corresponding INS output at certain time instants and do not consider the dependence of the error on the past values of INS. This study, therefore, suggests the use of Input-Delayed Neural Networks (IDNN) to model both the INS position and velocity errors based on current and some past samples of INS position and velocity, respectively. This results in a more reliable positioning solution during long GPS outages. The proposed method is evaluated using road test data of different trajectories while both navigational and tactical grade INS are mounted inside land vehicles and integrated with GPS receivers. The performance of the IDNN - based model is also compared to both conventional (based mainly on Kalman filtering) and recently published AI - based techniques. The results showed significant improvement in positioning accuracy especially for cases of tactical grade INS and long GPS outages.

    KW - Data fusion

    KW - Dynamic neural network

    KW - GPS

    KW - Inertial Navigation System (INS)

    KW - INS/GPS road tests

    UR - http://www.scopus.com/inward/record.url?scp=77956965234&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77956965234&partnerID=8YFLogxK

    U2 - 10.1016/j.inffus.2010.01.003

    DO - 10.1016/j.inffus.2010.01.003

    M3 - Article

    AN - SCOPUS:77956965234

    VL - 12

    SP - 48

    EP - 57

    JO - Information Fusion

    JF - Information Fusion

    SN - 1566-2535

    IS - 1

    ER -