Drift-free Visual SLAM using Digital Twins

TL;DR

This paper presents a novel drift-free visual SLAM method that aligns sparse 3D point clouds to digital twins for globally consistent localization, outperforming existing systems in accuracy and robustness.

Contribution

It introduces a new approach that aligns VIO/VSLAM generated point clouds to digital twins without visual data association, achieving drift-free, globally consistent localization.

Findings

Outperforms state-of-the-art VIO-GPS systems in accuracy.

Offers superior robustness against viewpoint changes.

Validated on high-fidelity GPS simulator and real drone data.

Abstract

Globally-consistent localization in urban environments is crucial for autonomous systems such as self-driving vehicles and drones, as well as assistive technologies for visually impaired people. Traditional Visual-Inertial Odometry (VIO) and Visual Simultaneous Localization and Mapping (VSLAM) methods, though adequate for local pose estimation, suffer from drift in the long term due to reliance on local sensor data. While GPS counteracts this drift, it is unavailable indoors and often unreliable in urban areas. An alternative is to localize the camera to an existing 3D map using visual-feature matching. This can provide centimeter-level accurate localization but is limited by the visual similarities between the current view and the map. This paper introduces a novel approach that achieves accurate and globally-consistent localization by aligning the sparse 3D point cloud generated by the VIO/VSLAM system to a digital twin using point-to-plane matching; no visual data association is needed. The proposed method provides a 6-DoF global measurement tightly integrated into the VIO/VSLAM system. Experiments run on a high-fidelity GPS simulator and real-world data collected from a drone demonstrate that our approach outperforms state-of-the-art VIO-GPS systems and offers superior robustness against viewpoint changes compared to the state-of-the-art Visual SLAM systems.