Odometry is a crucial task in the design of intelligent vehicles and there are many novel approaches with different sensors in Intelligent Transportation Systems (ITS) field. Accordingly, this leads to the use of multiple methods and sensors for identifying the vehicle pose in the environment, hence the necessity of multiple odometry sensors fusion methods. Quantifying the uncertainties of the sensors used in the vehicle is essential for utilizing effective fusion systems. Since the identification of the true values of the uncertainties is an exhaustive task, this paper introduces an online adaptive covariance estimation approach for drift suffering proprioceptive sensors, using an exteroceptive sensor with known uncertainty. To validate the proposed approach, three scenarios were selected and various experiments were carried out under different conditions. Though the use of multiple odometry sensors fusion algorithm, a comparative study was conducted between the adaptive covariance and several constant covariances based on the true variances. The obtained results show high performance of the proposed approach, in terms of four evaluation metrics for both translation and orientation mean errors.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Online Adaptive Covariance Estimation Approach for Multiple Odometry Sensors Fusion


    Contributors:


    Publication date :

    2018-06-01


    Size :

    951426 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Real-Time Visual Odometry Covariance Estimation for Unmanned Air Vehicle Navigation

    Anderson, Michael L. / Brink, Kevin M. / Willis, Andrew R. | AIAA | 2019



    2.5D vehicle odometry estimation

    Ciarán Eising / Leroy‐Francisco Pereira / Jonathan Horgan et al. | DOAJ | 2022

    Free access

    FUSION OF VISUAL AND WHEEL ODOMETRY WITH INTEGRATED SLIP ESTIMATION

    Malinowski, Mateusz T. / Richards, Arthur / Woods, Mark | TIBKAT | 2021


    2.5D vehicle odometry estimation

    Eising, Ciarán / Pereira, Leroy‐Francisco / Horgan, Jonathan et al. | Wiley | 2022

    Free access