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.
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.
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.
The alert did not successfully save. Please try again later.
Daniele Savio, 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