VIO-DualProNet: Visual-Inertial Odometry with Learning Based Process Noise Covariance

TL;DR

VIO-DualProNet introduces a deep learning approach to dynamically estimate inertial sensor noise in real-time, significantly improving the accuracy and robustness of visual-inertial odometry systems in diverse conditions.

Contribution

It presents a novel deep learning method to estimate inertial noise covariance dynamically, integrated into VINS-Mono, enhancing VIO performance over fixed noise assumptions.

Findings

Improved localization accuracy in VIO systems.

Enhanced robustness across varying sensor noise conditions.

Real-time inertial noise estimation outperforms fixed covariance methods.

Abstract

Visual-inertial odometry (VIO) is a vital technique used in robotics, augmented reality, and autonomous vehicles. It combines visual and inertial measurements to accurately estimate position and orientation. Existing VIO methods assume a fixed noise covariance for the inertial uncertainty. However, accurately determining in real-time the noise variance of the inertial sensors presents a significant challenge as the uncertainty changes throughout the operation leading to suboptimal performance and reduced accuracy. To circumvent this, we propose VIO-DualProNet, a novel approach that utilizes deep learning methods to dynamically estimate the inertial noise uncertainty in real-time. By designing and training a deep neural network to predict inertial noise uncertainty using only inertial sensor measurements, and integrating it into the VINS-Mono algorithm, we demonstrate a substantial improvement in accuracy and robustness, enhancing VIO performance and potentially benefiting other VIO-based systems for precise localization and mapping across diverse conditions.