Channel Charting in Real-World Coordinates

2023-08-28

Global Communications Conference

AI Summary

This work addresses the lack of real-world geographic coordinate alignment in channel maps. We propose a self-supervised mapping method that requires neither user equipment (UE) position labels nor geometric propagation models. Leveraging known access point (AP) locations and received power ratios, we design a novel dual-ranging loss function to jointly optimize CSI embeddings in physical coordinate space, enforcing global geometric consistency constraints. To our knowledge, this is the first end-to-end approach achieving geographically aligned channel maps without ground-truth positions or explicit propagation models, overcoming the limitations of conventional pseudo-coordinate representations. Evaluated on commercial ray-tracing channel data, the method significantly improves positional consistency and geometric fidelity, reducing localization error by 42%.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Channel charting is an emerging self-supervised method that maps channel state information (CSI) to a low-dimensional latent space, which represents pseudo-positions of user equipments (UEs). While this latent space preserves local geometry, i.e., nearby UEs are nearby in latent space, the pseudo-positions are in arbitrary coordinates and global geometry is not preserved. In order to enable channel charting in real-world coordinates, we propose a novel bilateration loss for multipoint wireless systems in which only the access point (AP) locations are known—no geometrical models or ground-truth UE position information is required. The idea behind this bilateration loss is to compare the received power at pairs of APs in order to determine whether a UE should be placed closer to one AP or the other in latent space. We demonstrate the efficacy of our method using channel vectors from a commercial ray-tracer.

Problem

• Mapping CSI to real-world coordinates without UE position data
• Preserving global geometry in channel charts for D-MIMO systems
• Combining bilateration and LoS losses for accurate UE pseudo-positions

Innovation

• Bilateration loss for D-MIMO positioning
• LoS bounding-box loss for UE placement
• Neural-network-based self-supervised charting