Visual Inertial Odometry (VIO) is one of the most established state estimation methods for mobile platforms. However, when visual tracking fails, VIO algorithms quickly diverge due to rapid error accumulation during inertial data integration. This error is typically modeled as a combination of additive Gaussian noise and a slowly changing bias which evolves as a random walk. In this work, we propose to train a neural network to learn the true bias evolution. We implement and compare two common sequential deep learning architectures: LSTMs and Transformers. Our approach follows from recent learning-based inertial estimators, but, instead of learning a motion model, we target IMU bias explicitly, which allows us to generalize to locomotion patterns unseen in training. We show that our proposed method improves state estimation in visually challenging situations across a wide range of motions by quadrupedal robots, walking humans, and drones. Our experiments show an average 15% reduction in drift rate, with much larger reductions when there is total vision failure. Importantly, we also demonstrate that models trained with one locomotion pattern (human walking) can be applied to another (quadruped robot trotting) without retraining.


    Access

    Download


    Export, share and cite



    Title :

    Deep IMU bias inference for robust visual-inertial odometry with factor graphs


    Contributors:
    Buchanan, R (author) / Agrawal, V (author) / Camurri, M (author) / Dellaert, F (author) / Fallon, M (author)

    Publication date :

    2022-11-16


    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    DDC:    629



    Robust Multispectral Visual-Inertial Navigation With Visual Odometry Failure Recovery

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


    Robust Visual-Inertial Odometry Based on a Kalman Filter and Factor Graph

    Wang, Zhiwei / Pang, Bao / Song, Yong et al. | IEEE | 2023


    VIDO: A Robust and Consistent Monocular Visual-Inertial-Depth Odometry

    Gao, Yuanxi / Yuan, Jing / Jiang, Jingqi et al. | IEEE | 2023


    Radar aided visual inertial odometry initialization

    NIESEN URS | European Patent Office | 2020

    Free access

    Visual-Inertial Odometry for Unmanned Aerial Vehicle using Deep Learning

    Lee, Hongyun / McCrink, Matthew / Gregory, James W. | AIAA | 2019