A Robust 5G Terrestrial Positioning System with Sensor Fusion in GNSS-denied Scenarios
Hamed Talebian, Nazrul Mohamed Nazeer, Darius Chmieliauskas, Jakub Nikonowicz, Mehdi Haghshenas, {\L}ukasz Matuszewski, Mairo Leier, Aamir Mahmood

TL;DR
This paper introduces a 5G-based terrestrial positioning system that fuses sensor data and employs deep learning to achieve accurate localization in GNSS-denied urban environments, demonstrating less than 5 meters error.
Contribution
It proposes a novel hybrid localization approach combining carrier phase ranging, deep learning link classification, and sensor fusion to improve accuracy and robustness in obstructed scenarios.
Findings
Achieves less than 5 meters positioning error in urban environments.
Uses deep learning to identify NLOS links and improve trilateration.
Demonstrates robustness through sensor fusion with IMUs and cameras.
Abstract
This paper presents a terrestrial localization system based on 5G infrastructure as a viable alternative to GNSS, particularly in scenarios where GNSS signals are obstructed or unavailable. It discusses network planning aimed at enabling positioning as a primary service, in contrast to the traditional focus on communication services in terrestrial networks. Building on a network infrastructure optimized for positioning, the paper proposes a system that leverages carrier phase (CP) ranging in combination with trilateration to localize the user within the network when at least three base stations (BSs) provide line-of-sight (LOS) conditions. Achieving accurate CP-based positioning requires addressing three key challenges: integer ambiguity resolution, LOS/NLOS link identification, and localization under obstructed LOS conditions. To this end, the system employs a multi-carrier CP…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
