Schur Complement Optimized Iterative EKF for Visual–Inertial Odometry in Autonomous Vehicles

Accuracy and nonlinear processing capabilities are critical to the positioning and navigation of autonomous vehicles in visual–inertial odometry (VIO). Existing filtering-based VIO methods struggle to deal with strongly nonlinear systems and often exhibit low precision. To this end, this paper propo...

Full description

Saved in:
Bibliographic Details
Main Authors: Guo Ma, Cong Li, Hui Jing, Bing Kuang, Ming Li, Xiang Wang, Guangyu Jia
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Machines
Subjects:
Online Access:https://www.mdpi.com/2075-1702/13/7/582
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246363320057856
author Guo Ma
Cong Li
Hui Jing
Bing Kuang
Ming Li
Xiang Wang
Guangyu Jia
author_facet Guo Ma
Cong Li
Hui Jing
Bing Kuang
Ming Li
Xiang Wang
Guangyu Jia
author_sort Guo Ma
collection DOAJ
description Accuracy and nonlinear processing capabilities are critical to the positioning and navigation of autonomous vehicles in visual–inertial odometry (VIO). Existing filtering-based VIO methods struggle to deal with strongly nonlinear systems and often exhibit low precision. To this end, this paper proposes a VIO method based on the Schur complement and Iterated Extended Kalman Filtering (IEKF). The algorithm first enhances ORB (Oriented FAST and Rotated BRIEF) features using Multi-Layer Perceptron (MLP) and Transformer architectures to improve feature robustness. It then integrates visual information and Inertial Measurement Unit (IMU) data through IEKF, constructing a complete residual model. The Schur complement is applied during covariance updates to compress the state dimension, improving computational efficiency and significantly enhancing the system’s ability to handle nonlinearities while maintaining real-time performance. Compared to traditional Extended Kalman Filtering (EKF), the proposed method demonstrates stronger stability and accuracy in high-dynamic scenarios. The experimental results show that the algorithm achieves superior state estimation performance on several typical visual–inertial datasets, demonstrating excellent accuracy and robustness.
format Article
id doaj-art-de07a9b19e6943cbbc68fa5e10514fb7
institution Kabale University
issn 2075-1702
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Machines
spelling doaj-art-de07a9b19e6943cbbc68fa5e10514fb72025-08-20T03:58:31ZengMDPI AGMachines2075-17022025-07-0113758210.3390/machines13070582Schur Complement Optimized Iterative EKF for Visual–Inertial Odometry in Autonomous VehiclesGuo Ma0Cong Li1Hui Jing2Bing Kuang3Ming Li4Xiang Wang5Guangyu Jia6Liuzhou Wuling Automobile Industry Co., Ltd., Liuzhou 545007, ChinaSchool of Mechanical and Electrical Engineering, Guilin University of Aerospace Technology, Guilin 541004, ChinaSchool of Mechanical and Electrical Engineering, Guilin University of Electronic Technology, Guilin 541200, ChinaSchool of Mechanical and Electrical Engineering, Guilin University of Electronic Technology, Guilin 541200, ChinaSchool of Mechanical and Electrical Engineering, Guilin University of Electronic Technology, Guilin 541200, ChinaSchool of Mechanical and Electrical Engineering, Guilin University of Electronic Technology, Guilin 541200, ChinaSchool of Mechanical and Electrical Engineering, Guilin University of Electronic Technology, Guilin 541200, ChinaAccuracy and nonlinear processing capabilities are critical to the positioning and navigation of autonomous vehicles in visual–inertial odometry (VIO). Existing filtering-based VIO methods struggle to deal with strongly nonlinear systems and often exhibit low precision. To this end, this paper proposes a VIO method based on the Schur complement and Iterated Extended Kalman Filtering (IEKF). The algorithm first enhances ORB (Oriented FAST and Rotated BRIEF) features using Multi-Layer Perceptron (MLP) and Transformer architectures to improve feature robustness. It then integrates visual information and Inertial Measurement Unit (IMU) data through IEKF, constructing a complete residual model. The Schur complement is applied during covariance updates to compress the state dimension, improving computational efficiency and significantly enhancing the system’s ability to handle nonlinearities while maintaining real-time performance. Compared to traditional Extended Kalman Filtering (EKF), the proposed method demonstrates stronger stability and accuracy in high-dynamic scenarios. The experimental results show that the algorithm achieves superior state estimation performance on several typical visual–inertial datasets, demonstrating excellent accuracy and robustness.https://www.mdpi.com/2075-1702/13/7/582autonomous vehiclesVIOIEKFSchur complementMLPtransformer
spellingShingle Guo Ma
Cong Li
Hui Jing
Bing Kuang
Ming Li
Xiang Wang
Guangyu Jia
Schur Complement Optimized Iterative EKF for Visual–Inertial Odometry in Autonomous Vehicles
Machines
autonomous vehicles
VIO
IEKF
Schur complement
MLP
transformer
title Schur Complement Optimized Iterative EKF for Visual–Inertial Odometry in Autonomous Vehicles
title_full Schur Complement Optimized Iterative EKF for Visual–Inertial Odometry in Autonomous Vehicles
title_fullStr Schur Complement Optimized Iterative EKF for Visual–Inertial Odometry in Autonomous Vehicles
title_full_unstemmed Schur Complement Optimized Iterative EKF for Visual–Inertial Odometry in Autonomous Vehicles
title_short Schur Complement Optimized Iterative EKF for Visual–Inertial Odometry in Autonomous Vehicles
title_sort schur complement optimized iterative ekf for visual inertial odometry in autonomous vehicles
topic autonomous vehicles
VIO
IEKF
Schur complement
MLP
transformer
url https://www.mdpi.com/2075-1702/13/7/582
work_keys_str_mv AT guoma schurcomplementoptimizediterativeekfforvisualinertialodometryinautonomousvehicles
AT congli schurcomplementoptimizediterativeekfforvisualinertialodometryinautonomousvehicles
AT huijing schurcomplementoptimizediterativeekfforvisualinertialodometryinautonomousvehicles
AT bingkuang schurcomplementoptimizediterativeekfforvisualinertialodometryinautonomousvehicles
AT mingli schurcomplementoptimizediterativeekfforvisualinertialodometryinautonomousvehicles
AT xiangwang schurcomplementoptimizediterativeekfforvisualinertialodometryinautonomousvehicles
AT guangyujia schurcomplementoptimizediterativeekfforvisualinertialodometryinautonomousvehicles