Learning Wheel Odometry and IMU Errors for Localization

Abstract : Odometry techniques are key to autonomous robot navigation, since they enable self-localization in the environment. However, designing a robust odometry system is particularly challenging when camera and LiDAR are uninformative or unavailable. In this paper, we leverage recent advances in deep learning and variational inference to correct dynamical and observation models for state-space systems. The methodology trains Gaussian processes on the residual between the original model and the ground truth, and is applied on publicly available datasets for robot navigation based on two wheel encoders, a fiber optic gyro, and an Inertial Measurement Unit (IMU). We also propose to build an Extended Kalman Filter (EKF) on the learned model using wheel speed sensors and the fiber optic gyro for state propagation, and the IMU to update the estimated state. Experimental results clearly demonstrate that the (learned) corrected models and EKF are more accurate than their original counterparts.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01874593
Contributor : Martin Brossard <>
Submitted on : Saturday, March 2, 2019 - 9:59:43 AM
Last modification on : Wednesday, March 13, 2019 - 1:24:39 AM

File

ICRA19_0036_FI.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01874593, version 2

Citation

Martin Brossard, Silvere Bonnabel. Learning Wheel Odometry and IMU Errors for Localization. International Conference on Robotics and Automation (ICRA), May 2019, Montreal, Canada. ⟨hal-01874593v2⟩

Share

Metrics

Record views

66

Files downloads

863