TY - JOUR
T1 - XR-RF Imaging Enabled by Software-Defined Metasurfaces and Machine Learning
T2 - Foundational Vision, Technologies and Challenges
AU - Liaskos, Christos
AU - Tsioliaridou, Ageliki
AU - Georgopoulos, Konstantinos
AU - Morianos, Ioannis
AU - Ioannidis, Sotiris
AU - Salem, Iosif
AU - Manessis, Dionyssios
AU - Schmid, Stefan
AU - Tyrovolas, Dimitrios
AU - Tegos, Sotiris A.
AU - Mekikis, Prodromos Vasileios
AU - Diamantoulakis, Panagiotis D.
AU - Pitilakis, Alexandros
AU - Kantartzis, Nikolaos V.
AU - Karagiannidis, George K.
AU - Tasolamprou, Anna C.
AU - Tsilipakos, Odysseas
AU - Kafesaki, Maria
AU - Akyildiz, Ian F.
AU - Pitsillides, Andreas
AU - Pateraki, Maria
AU - Vakalellis, Michael
AU - Spais, Ilias
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2022
Y1 - 2022
N2 - In this work, we present a new approach to Extended Reality (XR), denoted as iCOPYWAVES, which seeks to offer naturally low-latency operation and cost effectiveness, overcoming the critical scalability issues faced by existing solutions. Specifically, iCOPYWAVES is enabled by emerging PWEs, a recently proposed technology in wireless communications. Empowered by intelligent metasurfaces, PWEs transform the wave propagation phenomenon into a software-defined process. To this end, we leverage PWEs to: i) create, and then ii) selectively copy the scattered RF wavefront of an object from one location in space to another, where a machine learning module, accelerated by FPGAs, translates it to visual input for an XR headset using PWE-driven, RF imaging principles (XR-RF). This makes an XR system whose operation is bounded in the physical-layer and, hence, has the prospects for minimal end-to-end latency. For the case of large distances, RF-to-fiber/fiber-to-RF is employed to provide intermediate connectivity. The paper provides a tutorial on the iCOPYWAVES system architecture and workflow.
AB - In this work, we present a new approach to Extended Reality (XR), denoted as iCOPYWAVES, which seeks to offer naturally low-latency operation and cost effectiveness, overcoming the critical scalability issues faced by existing solutions. Specifically, iCOPYWAVES is enabled by emerging PWEs, a recently proposed technology in wireless communications. Empowered by intelligent metasurfaces, PWEs transform the wave propagation phenomenon into a software-defined process. To this end, we leverage PWEs to: i) create, and then ii) selectively copy the scattered RF wavefront of an object from one location in space to another, where a machine learning module, accelerated by FPGAs, translates it to visual input for an XR headset using PWE-driven, RF imaging principles (XR-RF). This makes an XR system whose operation is bounded in the physical-layer and, hence, has the prospects for minimal end-to-end latency. For the case of large distances, RF-to-fiber/fiber-to-RF is employed to provide intermediate connectivity. The paper provides a tutorial on the iCOPYWAVES system architecture and workflow.
KW - Extended/virtual/augmented reality
KW - XR-RF imaging
KW - applications
KW - generative adversarial networks
KW - machine learning
KW - propagation
KW - software-defined networking
KW - wireless
UR - http://www.scopus.com/inward/record.url?scp=85141609900&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2022.3219871
DO - 10.1109/ACCESS.2022.3219871
M3 - Article
AN - SCOPUS:85141609900
SN - 2169-3536
VL - 10
SP - 119841
EP - 119862
JO - IEEE Access
JF - IEEE Access
ER -