Enhancing Visual–Inertial Odometry Robustness and Accuracy in Challenging Environments

Visual–Inertial Odometry (VIO) algorithms are widely adopted for autonomous drone navigation in GNSS-denied environments. However, conventional monocular and stereo VIO setups often lack robustness under challenging environmental conditions or during aggressive maneuvers, due to the sensitivity of v...

Full description

Saved in:
Bibliographic Details
Main Authors: Alessandro Minervini, Adrian Carrio, Giorgio Guglieri
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Robotics
Subjects:
Online Access:https://www.mdpi.com/2218-6581/14/6/71
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850164630341550080
author Alessandro Minervini
Adrian Carrio
Giorgio Guglieri
author_facet Alessandro Minervini
Adrian Carrio
Giorgio Guglieri
author_sort Alessandro Minervini
collection DOAJ
description Visual–Inertial Odometry (VIO) algorithms are widely adopted for autonomous drone navigation in GNSS-denied environments. However, conventional monocular and stereo VIO setups often lack robustness under challenging environmental conditions or during aggressive maneuvers, due to the sensitivity of visual information to lighting, texture, and motion blur. In this work, we enhance an existing open-source VIO algorithm to improve both the robustness and accuracy of the pose estimation. First, we integrate an IMU-based motion prediction module to improve feature tracking across frames, particularly during high-speed movements. Second, we extend the algorithm to support a multi-camera setup, which significantly improves tracking performance in low-texture environments. Finally, to reduce the computational complexity, we introduce an adaptive feature selection strategy that dynamically adjusts the detection thresholds according to the number of detected features. Experimental results validate the proposed approaches, demonstrating notable improvements in both accuracy and robustness across a range of challenging scenarios.
format Article
id doaj-art-9bb325d53b3348a387abe30b39ede5cb
institution OA Journals
issn 2218-6581
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Robotics
spelling doaj-art-9bb325d53b3348a387abe30b39ede5cb2025-08-20T02:21:57ZengMDPI AGRobotics2218-65812025-05-011467110.3390/robotics14060071Enhancing Visual–Inertial Odometry Robustness and Accuracy in Challenging EnvironmentsAlessandro Minervini0Adrian Carrio1Giorgio Guglieri2Departement of Aerospace and Mechanical Engineering, Politecnico di Torino, Corso Duca degli Abruzzi 24, 1029 Torino, TO, ItalyDronomy, Paseo de la Castellana 40, 8th Floor, 28046 Madrid, SpainDepartement of Aerospace and Mechanical Engineering, Politecnico di Torino, Corso Duca degli Abruzzi 24, 1029 Torino, TO, ItalyVisual–Inertial Odometry (VIO) algorithms are widely adopted for autonomous drone navigation in GNSS-denied environments. However, conventional monocular and stereo VIO setups often lack robustness under challenging environmental conditions or during aggressive maneuvers, due to the sensitivity of visual information to lighting, texture, and motion blur. In this work, we enhance an existing open-source VIO algorithm to improve both the robustness and accuracy of the pose estimation. First, we integrate an IMU-based motion prediction module to improve feature tracking across frames, particularly during high-speed movements. Second, we extend the algorithm to support a multi-camera setup, which significantly improves tracking performance in low-texture environments. Finally, to reduce the computational complexity, we introduce an adaptive feature selection strategy that dynamically adjusts the detection thresholds according to the number of detected features. Experimental results validate the proposed approaches, demonstrating notable improvements in both accuracy and robustness across a range of challenging scenarios.https://www.mdpi.com/2218-6581/14/6/71VIOmulti-cameralocalizationGNSS-denieddronesrobotics
spellingShingle Alessandro Minervini
Adrian Carrio
Giorgio Guglieri
Enhancing Visual–Inertial Odometry Robustness and Accuracy in Challenging Environments
Robotics
VIO
multi-camera
localization
GNSS-denied
drones
robotics
title Enhancing Visual–Inertial Odometry Robustness and Accuracy in Challenging Environments
title_full Enhancing Visual–Inertial Odometry Robustness and Accuracy in Challenging Environments
title_fullStr Enhancing Visual–Inertial Odometry Robustness and Accuracy in Challenging Environments
title_full_unstemmed Enhancing Visual–Inertial Odometry Robustness and Accuracy in Challenging Environments
title_short Enhancing Visual–Inertial Odometry Robustness and Accuracy in Challenging Environments
title_sort enhancing visual inertial odometry robustness and accuracy in challenging environments
topic VIO
multi-camera
localization
GNSS-denied
drones
robotics
url https://www.mdpi.com/2218-6581/14/6/71
work_keys_str_mv AT alessandrominervini enhancingvisualinertialodometryrobustnessandaccuracyinchallengingenvironments
AT adriancarrio enhancingvisualinertialodometryrobustnessandaccuracyinchallengingenvironments
AT giorgioguglieri enhancingvisualinertialodometryrobustnessandaccuracyinchallengingenvironments