Modèle et algorithmes pour des systèmes de communication fiables (MARACAS), CITI Centre of Innovation in Telecommunications and Integration of services (CITI), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre Inria de Lyon, Institut National de Recherche en Informatique et en Automatique (Inria), Université de Lyon-Institut National des Sciences Appliquées (INSA), Centre Inria de Lyon, Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria), Université de Genève = University of Geneva (UNIGE), Laboratoire des signaux et systèmes (L2S), CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), King‘s College London, ANR-23-CHR4-0001,CHASER,Channel Charting as a Service(2023), European Project: 101139161,HORIZON-JU-SNS-2023,HORIZON-JU-SNS-2023,INSTINCT(2024)
Source:
Asilomar Conference on Signals, Systems, and Computers, Oct 2025, Pacific Grove, CA, United States
info:eu-repo/grantAgreement//101139161/EU/Joint Sensing and Communications for Future Interactive, Immersive, and Intelligent Connectivity Beyond Communications/INSTINCT
This work explores the extension of channel charting, a technique for constructing low-dimensional representations of channel state information (CSI) through self-supervised learning, to wireless environments including reconfigurable intelligent surfaces (RIS). Channel charting has shown promise in pseudoposition based radio resource management applications by capturing spatial relationships between transmitters and receivers. We investigate the challenges and opportunities that RISs present to channel charting, particularly focusing on how RIS reconfiguration affects the learned low-dimensional representations. We focus on a contrastive learning framework with triplet loss to derive a channel chart through distance learning, and incorporate the RIS configuration information into the learning process, aiming to develop channel charts that are robust to changes in the RIS configuration. We also explore the potential for leveraging channel charts to inform RIS configuration, enabling applications where the channel chart is used to determine optimal RIS settings from a given codebook.
