Denoising IMU Gyroscopes with Deep Learning for Open-Loop Attitude Estimation - CAO et robotique (CAOR) Accéder directement au contenu
Article Dans Une Revue IEEE Robotics and Automation Letters Année : 2020

Denoising IMU Gyroscopes with Deep Learning for Open-Loop Attitude Estimation

Résumé

This paper proposes a learning method for denoising gyroscopes of Inertial Measurement Units (IMUs) using ground truth data, and estimating in real time the orientation (attitude) of a robot in dead reckoning. The obtained algorithm outperforms the state-of-the-art on the (unseen) test sequences. The obtained performances are achieved thanks to a well-chosen model, a proper loss function for orientation increments, and through the identification of key points when training with high-frequency inertial data. Our approach builds upon a neural network based on dilated convolutions, without requiring any recurrent neural network. We demonstrate how efficient our strategy is for 3D attitude estimation on the EuRoC and TUM-VI datasets. Interestingly, we observe our dead reckoning algorithm manages to beat top-ranked visual-inertial odometry systems in terms of attitude estimation although it does not use vision sensors. We believe this paper offers new perspectives for visual-inertial localization and constitutes a step toward more efficient learning methods involving IMUs. Our open-source implementation is available at https://github.com/mbrossar/denoise-imu-gyro.
Fichier principal
Vignette du fichier
main (1).pdf (1.27 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02488923 , version 1 (24-02-2020)
hal-02488923 , version 2 (13-06-2020)
hal-02488923 , version 3 (02-07-2020)

Identifiants

Citer

Martin Brossard, Silvere Bonnabel, Axel Barrau. Denoising IMU Gyroscopes with Deep Learning for Open-Loop Attitude Estimation. IEEE Robotics and Automation Letters, inPress. ⟨hal-02488923v3⟩
187 Consultations
554 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More