Learned Integrated Sensing Pipeline: Reconfigurable Metasurface Transceivers as Trainable Physical Layer in an Artificial Neural Network

Philipp del Hougne, Mohammadreza F. Imani, Aaron V. Diebold, Roarke Horstmeyer, David R. Smith

Research output: Contribution to journalArticlepeer-review

13 Scopus citations

Abstract

The rapid proliferation of intelligent systems (e.g., fully autonomous vehicles) in today's society relies on sensors with low latency and computational effort. Yet current sensing systems ignore most available a priori knowledge, notably in the design of the hardware level, such that they fail to extract as much task-relevant information per measurement as possible. Here, a “learned integrated sensing pipeline” (LISP), including in an end-to-end fashion both physical and processing layers, is shown to enable joint learning of optimal measurement strategies and a matching processing algorithm, making use of a priori knowledge on task, scene, and measurement constraints. Numerical results demonstrate accuracy improvements around 15% for object recognition tasks with limited numbers of measurements, using dynamic metasurface apertures capable of transceiving programmable microwave patterns. Moreover, it is concluded that the optimal learned microwave patterns are nonintuitive, underlining the importance of the LISP paradigm in current sensorization trends.

Original languageEnglish (US)
Article number1901913
JournalAdvanced Science
Volume7
Issue number3
DOIs
StatePublished - Feb 1 2020
Externally publishedYes

Keywords

  • machine learning
  • metasurfaces
  • sensing
  • wavefront shaping

ASJC Scopus subject areas

  • Medicine (miscellaneous)
  • Chemical Engineering(all)
  • Biochemistry, Genetics and Molecular Biology (miscellaneous)
  • Materials Science(all)
  • Engineering(all)
  • Physics and Astronomy(all)

Fingerprint Dive into the research topics of 'Learned Integrated Sensing Pipeline: Reconfigurable Metasurface Transceivers as Trainable Physical Layer in an Artificial Neural Network'. Together they form a unique fingerprint.

Cite this