Machine learning assisted control of integrated optical phased arrays

Daniele Savio; Paolo Bardella

doi:10.1117/12.2608198

5 March 2022 Machine learning assisted control of integrated optical phased arrays

Daniele Savio, Paolo Bardella

Proceedings Volume 12005, Smart Photonic and Optoelectronic Integrated Circuits 2022; 1200508 (2022) https://doi.org/10.1117/12.2608198
Event: SPIE OPTO, 2022, San Francisco, California, United States

Abstract

We propose a Machine Learning (ML) based approach to calculate the control signals to apply to an integrated Optical Phased Array (OPA) to get the desired far field profile, which is of particular interest for single-pixel imaging applications. We validated this approach considering a 1D OPA with 8 thermally controlled input waveguides and an 8x1 combiner. We generated 7500 random combinations of the 8 control signals, performing BPM simulations in Synopsys RSoft to calculate far field intensity maps later used to train in MATLAB the ML algorithm. The trained network can then generate the control signals required to obtain any desired far field pattern.

Conference Presentation

Citation Download Citation

Daniele Savio and Paolo Bardella "Machine learning assisted control of integrated optical phased arrays", Proc. SPIE 12005, Smart Photonic and Optoelectronic Integrated Circuits 2022, 1200508 (5 March 2022); https://doi.org/10.1117/12.2608198

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available