Learned IMU Bias Prediction for Invariant Visual Inertial Odometry

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Altawaitan, Abdullah, Stanley, Jason, Ghosal, Sambaran, Duong, Thai, Atanasov, Nikolay
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914072229838848
author Altawaitan, Abdullah
Stanley, Jason
Ghosal, Sambaran
Duong, Thai
Atanasov, Nikolay
author_facet Altawaitan, Abdullah
Stanley, Jason
Ghosal, Sambaran
Duong, Thai
Atanasov, Nikolay
contents Autonomous mobile robots operating in novel environments depend critically on accurate state estimation, often utilizing visual and inertial measurements. Recent work has shown that an invariant formulation of the extended Kalman filter improves the convergence and robustness of visual-inertial odometry by utilizing the Lie group structure of a robot's position, velocity, and orientation states. However, inertial sensors also require measurement bias estimation, yet introducing the bias in the filter state breaks the Lie group symmetry. In this paper, we design a neural network to predict the bias of an inertial measurement unit (IMU) from a sequence of previous IMU measurements. This allows us to use an invariant filter for visual inertial odometry, relying on the learned bias prediction rather than introducing the bias in the filter state. We demonstrate that an invariant multi-state constraint Kalman filter (MSCKF) with learned bias predictions achieves robust visual-inertial odometry in real experiments, even when visual information is unavailable for extended periods and the system needs to rely solely on IMU measurements.
format Preprint
id arxiv_https___arxiv_org_abs_2505_06748
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learned IMU Bias Prediction for Invariant Visual Inertial Odometry
Altawaitan, Abdullah
Stanley, Jason
Ghosal, Sambaran
Duong, Thai
Atanasov, Nikolay
Robotics
Autonomous mobile robots operating in novel environments depend critically on accurate state estimation, often utilizing visual and inertial measurements. Recent work has shown that an invariant formulation of the extended Kalman filter improves the convergence and robustness of visual-inertial odometry by utilizing the Lie group structure of a robot's position, velocity, and orientation states. However, inertial sensors also require measurement bias estimation, yet introducing the bias in the filter state breaks the Lie group symmetry. In this paper, we design a neural network to predict the bias of an inertial measurement unit (IMU) from a sequence of previous IMU measurements. This allows us to use an invariant filter for visual inertial odometry, relying on the learned bias prediction rather than introducing the bias in the filter state. We demonstrate that an invariant multi-state constraint Kalman filter (MSCKF) with learned bias predictions achieves robust visual-inertial odometry in real experiments, even when visual information is unavailable for extended periods and the system needs to rely solely on IMU measurements.
title Learned IMU Bias Prediction for Invariant Visual Inertial Odometry
topic Robotics
url https://arxiv.org/abs/2505.06748