TY - GEN

T1 - Pose estimation of optical resonators using convolutional neural networks in a simulation environment

AU - Melchert, Nils Frederik

AU - Hedrich, Kolja

AU - Wiese, Leon Vincent

AU - Hinz, Lennart

AU - Reithmeier, Eduard

N1 - Conference code: 122250E

PY - 2022/10/3

Y1 - 2022/10/3

N2 - External Fabry-Perot resonators are widely used in the field of optics and are well established in areas such as frequency selection and spectroscopy. However, fine tuning and thus most efficient coupling of these resonators into the optical path is a time-consuming task, which is usually performed manually by trained personnel. The state of the art includes many different approaches for automatic alignment, which, however, are designed for special optical configurations and cannot be generalized. However, these approaches are only valid for individually designed optical systems and are not universally applicable. Moreover, none of these approaches address the identification of the spatial degrees of freedom of the resonator. Knowledge of this exact pose information can generally be integrated into the alignment process and has great potential for automation. In this work, convolutional neural networks (CNNs) are applied to identify the sensitive spatial degrees of freedom of a FabryPerot resonator in a simulation environment. For this purpose, well established CNN architectures, which are typically used for feature extraction, are adapted to this regression problem. The input of the CNNs was chosen to be the intensity profiles of the transversal modes, which can be obtained from the transmitted power behind the resonator. These modes are known to be highly correlated with the coupling quality and thus with the spatial location of resonators. To achieve an exact pose estimation, the CNN input consists of several images of mode profiles, which are propagated through an encoder structure followed by fully-connected layers providing the four spatial parameters as the network output. For training and evaluation, intensity images as well as resonator poses are obtained from a simulation of a free spectral range of a resonator. Finally, different encoder structures including a memory efficient, small self-developed network architecture are evaluated.

AB - External Fabry-Perot resonators are widely used in the field of optics and are well established in areas such as frequency selection and spectroscopy. However, fine tuning and thus most efficient coupling of these resonators into the optical path is a time-consuming task, which is usually performed manually by trained personnel. The state of the art includes many different approaches for automatic alignment, which, however, are designed for special optical configurations and cannot be generalized. However, these approaches are only valid for individually designed optical systems and are not universally applicable. Moreover, none of these approaches address the identification of the spatial degrees of freedom of the resonator. Knowledge of this exact pose information can generally be integrated into the alignment process and has great potential for automation. In this work, convolutional neural networks (CNNs) are applied to identify the sensitive spatial degrees of freedom of a FabryPerot resonator in a simulation environment. For this purpose, well established CNN architectures, which are typically used for feature extraction, are adapted to this regression problem. The input of the CNNs was chosen to be the intensity profiles of the transversal modes, which can be obtained from the transmitted power behind the resonator. These modes are known to be highly correlated with the coupling quality and thus with the spatial location of resonators. To achieve an exact pose estimation, the CNN input consists of several images of mode profiles, which are propagated through an encoder structure followed by fully-connected layers providing the four spatial parameters as the network output. For training and evaluation, intensity images as well as resonator poses are obtained from a simulation of a free spectral range of a resonator. Finally, different encoder structures including a memory efficient, small self-developed network architecture are evaluated.

KW - Fabry-Perot resonator

KW - Neural networks

KW - Optical assembly

KW - Optical pose estimation

UR - http://www.scopus.com/inward/record.url?scp=85140344866&partnerID=8YFLogxK

U2 - 10.1117/12.2633416

DO - 10.1117/12.2633416

M3 - Conference contribution

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Optical System Alignment, Tolerancing, and Verification XIV

A2 - Sasian, Jose

A2 - Youngworth, Richard N.

PB - SPIE

T2 - SPIE Optical Engineering + Applications, 2022, San Diego, California, United States

Y2 - 21 August 2022 through 25 August 2022

ER -