2024/07/28 by Gouranga Charan, Charan, Gouranga, Tawfik Osman +3 · 1 citation
Computer Science · Engineering · #FOS: Electrical engineering #Image and Object Detection Techniques #Inertial Sensor and Navigation #Robotics and Sensor-Based Localization #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2407.19541
openalex publication_date 2024/07/28 · openalex created_date 2024/08/01 · openalex updated_date 2026/07/28
Accurate localization is crucial for various applications, including autonomous vehicles and next-generation wireless networks. However, the reliability and precision of Global Navigation Satellite Systems (GNSS), such as the Global Positioning System (GPS), are compromised by multi-path errors and non-line-of-sight scenarios. This paper presents a novel approach to enhance GPS accuracy by combining visual data from RGB cameras with wireless signals captured at millimeter-wave (mmWave) and sub-terahertz (sub-THz) basestations. We propose a sensing-aided framework for (i) site-specific GPS data characterization and (ii) GPS position de-noising that utilizes multi-modal visual and wireless information. Our approach is validated in a realistic Vehicle-to-Infrastructure (V2I) scenario using a comprehensive real-world dataset, demonstrating a substantial reduction in localization error to sub-meter levels. This method represents a significant advancement in achieving precise localization, particularly beneficial for high-mobility applications in 5G and beyond networks.