Adaptive VIO: Deep Visual-Inertial Odometry with Online Continual Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pan, Youqi, Zhou, Wugen, Cao, Yingdian, Zha, Hongbin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909211177254912
author Pan, Youqi
Zhou, Wugen
Cao, Yingdian
Zha, Hongbin
author_facet Pan, Youqi
Zhou, Wugen
Cao, Yingdian
Zha, Hongbin
contents Visual-inertial odometry (VIO) has demonstrated remarkable success due to its low-cost and complementary sensors. However, existing VIO methods lack the generalization ability to adjust to different environments and sensor attributes. In this paper, we propose Adaptive VIO, a new monocular visual-inertial odometry that combines online continual learning with traditional nonlinear optimization. Adaptive VIO comprises two networks to predict visual correspondence and IMU bias. Unlike end-to-end approaches that use networks to fuse the features from two modalities (camera and IMU) and predict poses directly, we combine neural networks with visual-inertial bundle adjustment in our VIO system. The optimized estimates will be fed back to the visual and IMU bias networks, refining the networks in a self-supervised manner. Such a learning-optimization-combined framework and feedback mechanism enable the system to perform online continual learning. Experiments demonstrate that our Adaptive VIO manifests adaptive capability on EuRoC and TUM-VI datasets. The overall performance exceeds the currently known learning-based VIO methods and is comparable to the state-of-the-art optimization-based methods.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16754
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adaptive VIO: Deep Visual-Inertial Odometry with Online Continual Learning
Pan, Youqi
Zhou, Wugen
Cao, Yingdian
Zha, Hongbin
Robotics
Visual-inertial odometry (VIO) has demonstrated remarkable success due to its low-cost and complementary sensors. However, existing VIO methods lack the generalization ability to adjust to different environments and sensor attributes. In this paper, we propose Adaptive VIO, a new monocular visual-inertial odometry that combines online continual learning with traditional nonlinear optimization. Adaptive VIO comprises two networks to predict visual correspondence and IMU bias. Unlike end-to-end approaches that use networks to fuse the features from two modalities (camera and IMU) and predict poses directly, we combine neural networks with visual-inertial bundle adjustment in our VIO system. The optimized estimates will be fed back to the visual and IMU bias networks, refining the networks in a self-supervised manner. Such a learning-optimization-combined framework and feedback mechanism enable the system to perform online continual learning. Experiments demonstrate that our Adaptive VIO manifests adaptive capability on EuRoC and TUM-VI datasets. The overall performance exceeds the currently known learning-based VIO methods and is comparable to the state-of-the-art optimization-based methods.
title Adaptive VIO: Deep Visual-Inertial Odometry with Online Continual Learning
topic Robotics
url https://arxiv.org/abs/2405.16754