CSI-Based User Positioning, Channel Charting, and Device Classification with an NVIDIA 5G Testbed

2025-12-11

AI Summary

Existing research suffers from a critical scarcity of wideband channel state information (CSI) datasets collected from real-world 5G New Radio (NR) systems, hindering the development and validation of sensing algorithms. To address this, we introduce the first publicly available 5G NR CSI dataset acquired from a real multi-O-RU Open Radio Access Network (O-RAN) deployment, encompassing diverse indoor/outdoor environments and six commercial user equipment (UE) types. Methodologically, we leverage the NVIDIA Aerial RAN CoLab over-the-air (OTA) platform, integrating software-defined 5G NR, multi-antenna CSI acquisition, and deep neural networks (CNN/LSTM) within a unified channel feature engineering and real-coordinate mapping framework. Key contributions include: (1) the first open-source, multi-antenna, multi-O-RU 5G NR CSI dataset; (2) centimeter-level UE localization (0.6 cm indoors, 5.7 cm outdoors); (3) high-accuracy channel mapping (outdoor MAE = 73 cm); and (4) robust device classification (99% same-day, 95% cross-day accuracy). All data, labels, features, and code are publicly released.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Channel-state information (CSI)-based sensing will play a key role in future cellular systems. However, no CSI dataset has been published from a real-world 5G NR system that facilitates the development and validation of suitable sensing algorithms. To close this gap, we publish three real-world wideband multi-antenna multi-open RAN radio unit (O-RU) CSI datasets from the 5G NR uplink channel: an indoor lab/office room dataset, an outdoor campus courtyard dataset, and a device classification dataset with six commercial-off-the-shelf (COTS) user equipments (UEs). These datasets have been recorded using a software-defined 5G NR testbed based on NVIDIA Aerial RAN CoLab Over-the-Air (ARC-OTA) with COTS hardware, which we have deployed at ETH Zurich. We demonstrate the utility of these datasets for three CSI-based sensing tasks: neural UE positioning, channel charting in real-world coordinates, and closed-set device classification. For all these tasks, our results show high accuracy: neural UE positioning achieves 0.6cm (indoor) and 5.7cm (outdoor) mean absolute error, channel charting in real-world coordinates achieves 73cm mean absolute error (outdoor), and device classification achieves 99% (same day) and 95% (next day) accuracy. The CSI datasets, ground-truth UE position labels, CSI features, and simulation code are publicly available at https://caez.ethz.ch

Problem

• Addresses the lack of real-world 5G CSI datasets for sensing algorithm development
• Publishes three 5G NR uplink CSI datasets from indoor, outdoor, and device classification scenarios
• Demonstrates high-accuracy CSI-based sensing for positioning, charting, and device classification

Innovation

• Publishes real-world 5G NR CSI datasets from NVIDIA testbed
• Demonstrates neural UE positioning with centimeter-level accuracy
• Enables channel charting and device classification using CSI features