Toward Consistent Drift-free Visual Inertial Localization on Keyframe Based Map

TL;DR

This paper presents a novel global localization framework using a filter-based visual-inertial odometry approach that maintains consistency and reduces computational load by using keyframe poses and a re-linearization mechanism.

Contribution

It introduces a new framework combining Schmidt-EKF with keyframe pose maintenance and a re-linearization mechanism for improved accuracy and efficiency in visual-inertial localization.

Findings

Framework maintains state estimator consistency.

Re-linearization improves accuracy in large scenes.

Effective in simulations and real-world experiments.

Abstract

Global localization is essential for robots to perform further tasks like navigation. In this paper, we propose a new framework to perform global localization based on a filter-based visual-inertial odometry framework MSCKF. To reduce the computation and memory consumption, we only maintain the keyframe poses of the map and employ Schmidt-EKF to update the state. This global localization framework is shown to be able to maintain the consistency of the state estimator. Furthermore, we introduce a re-linearization mechanism during the updating phase. This mechanism could ease the linearization error of observation function to make the state estimation more precise. The experiments show that this mechanism is crucial for large and challenging scenes. Simulations and experiments demonstrate the effectiveness and consistency of our global localization framework.