Channel Charting for Position and Orientation

2026-06-16

AI Summary

This work addresses the challenge of user equipment localization and orientation estimation in 5G systems under label-free scenarios by proposing a self-supervised learning approach based on channel state information (CSI). The method integrates orientation estimation into the CSI fingerprinting framework for the first time, leveraging an orientation-aware triplet loss that accounts for angular periodicity and a self-supervised alignment loss designed to align embeddings with real-world coordinates. Experimental results on real-world 5G NR measurements demonstrate that the proposed approach achieves localization and orientation estimation accuracy comparable to supervised learning methods—despite requiring no ground-truth labels—thereby significantly advancing the practical deployment of self-supervised wireless sensing.

Abstract

Channel charting (CC) in real-world coordinates is a recently proposed self-supervised machine learning method that maps high-dimensional channel state information (CSI) to user equipment (UE) position. In this paper, we extend CC to also estimate UE orientation, which can further assist tasks such as beamfinding, precoding, and beam- and cell-assignment. To this end, we propose a novel orientation triplet loss that accounts for angle periodicity and an alignment loss that embeds estimated orientations in real-world coordinates in a self-supervised fashion. Using real-world CSI measurements from a standard-compliant 5G NR system, we demonstrate that the proposed method achieves position and orientation estimation accuracy close to that of supervised approaches trained with ground-truth labels.

Problem

• Channel Charting
• Position Estimation
• Orientation Estimation
• CSI
• 5G NR

Innovation

• Channel Charting
• Orientation Estimation
• Self-supervised Learning
• Triplet Loss
• 5G NR