In this paper, an Unmanned Aerial System (UAS) navigation solution using the Intel RealSense T265, a commercially available Visual Inertial Odometry device, is developed and presented in conjunction with an Extended Kalman Filter framework. Comparisons of raw and estimated position and yaw angle data from the device are made against ground truth measurements obtained via a motion capture system. Preliminary results from hand-carry tests show promising localization capability as the device continues to gather information about its environment. Further localization improvements may be achievable with varied software configurations. The performance of the Extended Kalman Filter during closed-loop flight is also evaluated, and shows smoothing of noisy measurements from the T265 and generally precise trajectory following capabilities. Future work to extend this characterization shall involve testing the performance of the device across varying flight envelopes, and especially for longer durations.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Evaluation of a Commercially Available Autonomous Visual Inertial Odometry Solution for Indoor Navigation


    Contributors:


    Publication date :

    2020-09-01


    Size :

    4288217 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    AUTONOMOUS NAVIGATION USING VISUAL ODOMETRY

    LIAO MIAO / LI MING / HONG SOONHAC | European Patent Office | 2017

    Free access

    Robust Multispectral Visual-Inertial Navigation With Visual Odometry Failure Recovery

    Beauvisage, Axel / Ahiska, Kenan / Aouf, Nabil | IEEE | 2022


    Visual Odometry for Autonomous Deep-Space Navigation

    Robinson, Shane / Pedrotty, Sam | NTRS | 2016


    WHEEL ODOMETRY AIDED VISUAL-INERTIAL ODOMETRY FOR LAND VEHICLE NAVIGATION IN WINTER URBAN ENVIRONMENTS

    Huang, Cheng / Jiang, Yang / O Keefe, Kyle | British Library Conference Proceedings | 2020


    Visual Odometry for Autonomous Deep-Space Navigation Project

    Robinson, Shane / Pedrotty, Sam | NTRS | 2016