Integration of Visual SLAM into Consumer-Grade Automotive Localization

TL;DR

This paper explores integrating visual SLAM into consumer vehicle localization to enhance accuracy, demonstrating improved gyroscope calibration and overall positioning performance through a novel fusion framework tested on various datasets.

Contribution

The paper introduces a new framework that fuses visual SLAM with vehicle dynamics for online gyroscope calibration in consumer vehicles, a largely unexplored area.

Findings

Significant improvement in gyroscope calibration accuracy.

Enhanced overall localization performance.

Superior results on public benchmark datasets.

Abstract

Accurate ego-motion estimation in consumer-grade vehicles currently relies on proprioceptive sensors, i.e. wheel odometry and IMUs, whose performance is limited by systematic errors and calibration. While visual-inertial SLAM has become a standard in robotics, its integration into automotive ego-motion estimation remains largely unexplored. This paper investigates how visual SLAM can be integrated into consumer-grade vehicle localization systems to improve performance. We propose a framework that fuses visual SLAM with a lateral vehicle dynamics model to achieve online gyroscope calibration under realistic driving conditions. Experimental results demonstrate that vision-based integration significantly improves gyroscope calibration accuracy and thus enhances overall localization performance, highlighting a promising path toward higher automotive localization accuracy. We provide results on both proprietary and public datasets, showing improved performance and superior localization accuracy on a public benchmark compared to state-of-the-art methods.