Modern robotic platforms need a reliable localization system to operate daily beside humans. Simple pose estimation algorithms based on filtered wheel and inertial odometry often fail in the presence of abrupt kinematic changes and wheel slips. Moreover, despite the recent success of visual odometry, service and assistive robotic tasks often present challenging environmental conditions where visual-based solutions fail due to poor lighting or repetitive feature patterns. In this work, we propose an innovative online learning approach for wheel odometry correction, paving the way for a robust multi-source localization system. An efficient attention-based neural network architecture has been studied to combine precise performances with realtime inference. The proposed solution shows remarkable results compared to a standard neural network and filter-based odometry correction algorithms. Nonetheless, the online learning paradigm avoids the time-consuming data collection procedure and can be adopted on a generic robotic platform on-the-fly.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Online Learning of Wheel Odometry Correction for Mobile Robots with Attention-based Neural Network



    Erscheinungsdatum :

    2023-01-01



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Mixed marker-based/marker-less visual odometry system for mobile robots

    LAMBERTI, FABRIZIO / SANNA, Andrea / PARAVATI, GIANLUCA et al. | BASE | 2013

    Freier Zugriff


    GPS-aided Visual Wheel Odometry

    Song, Junlin / Sanchez-Cuevas, Pedro J. / Richard, Antoine et al. | IEEE | 2023


    Odometry 2.0: A Slip-Adaptive EIF-Based Four-Wheel-Odometry Model for Parking

    Brunker, Alexander / Wohlgemuth, Thomas / Frey, Michael et al. | IEEE | 2019


    Attention Guided Unsupervised learning of Monocular Visual-inertial Odometry

    Wang, Zhenke / Zhu, Yuan / Lu, Ke et al. | IEEE | 2022