Look to Locate: Vision-Based Multisensory Navigation with 3-D Digital Maps for GNSS-Challenged Environments

2025-06-24

AI Summary

To address the challenge of high-accuracy, robust vehicle localization in GNSS-denied environments (e.g., indoor parking garages, urban canyons), this paper proposes a monocular vision–dominant multi-sensor fusion navigation method. The approach innovatively fuses monocular depth estimation and semantic segmentation outputs to construct a lightweight semantic-geometric feature representation, enabling real-time registration with a 3D digital map; inertial measurement unit (IMU) data are further integrated to suppress drift accumulation. Crucially, the method operates without GPS, significantly reducing long-term pose drift while enhancing cross-scene adaptability and scalability. Experimental validation demonstrates sub-meter accuracy: 92% of indoor and over 80% of outdoor position estimates exhibit errors under 1 m. The horizontal position and heading root-mean-square errors (RMSEs) are 0.98 m and 1.25°, respectively—representing an ~88% improvement over baseline methods.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Multi-modal Vision
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services

Abstract

In Global Navigation Satellite System (GNSS)-denied environments such as indoor parking structures or dense urban canyons, achieving accurate and robust vehicle positioning remains a significant challenge. This paper proposes a cost-effective, vision-based multi-sensor navigation system that integrates monocular depth estimation, semantic filtering, and visual map registration (VMR) with 3-D digital maps. Extensive testing in real-world indoor and outdoor driving scenarios demonstrates the effectiveness of the proposed system, achieving sub-meter accuracy of 92% indoors and more than 80% outdoors, with consistent horizontal positioning and heading average root mean-square errors of approximately 0.98 m and 1.25 °, respectively. Compared to the baselines examined, the proposed solution significantly reduced drift and improved robustness under various conditions, achieving positioning accuracy improvements of approximately 88% on average. This work highlights the potential of cost-effective monocular vision systems combined with 3D maps for scalable, GNSS-independent navigation in land vehicles.

Problem

• Achieving accurate vehicle positioning in GNSS-denied environments
• Integrating vision and sensors with 3D maps for navigation
• Reducing drift and improving robustness in challenging conditions

Innovation

• Monocular depth estimation for 3D mapping
• Semantic filtering enhances visual accuracy
• Visual map registration with digital maps