Lens Bending with Reinforcement Learning for Reduced Optical Aberrations

Frontiers in Optics + Laser Science (FiO, LS), pp. FM3C.7

Abstract

To automate optical system design, a Reinforcement Learning algorithm using lens improvement methods as parameter optimization or lens adding is developed. A proof of concept using lens bending is demonstrated for different learning strategies.

Authors 3

1. Cailing Fu corresponding Aachen Chair for Technology of Optical Systems TOS

   RWTH Aachen University

   Affiliation as printed

   Chair for Technology of Optical Systems TOS, RWTH Aachen University, Steinbachstraße 15, 52074 Aachen, Germany

2. Jochen Stollenwerk Aachen Chair for Technology of Optical Systems TOS Fraunhofer Institute for Laser Technology ILT

   RWTH Aachen University · Fraunhofer Institute for Laser Technology

   Affiliation as printed

   Chair for Technology of Optical Systems TOS, RWTH Aachen University, Steinbachstraße 15, 52074 Aachen, Germany

   Fraunhofer-Institute for Laser Technology ILT, Steinbachstr. 15, 52074 Aachen, Germany

3. Carlo Holly Aachen Chair for Technology of Optical Systems TOS

   RWTH Aachen University

   Affiliation as printed

   Chair for Technology of Optical Systems TOS, RWTH Aachen University, Steinbachstraße 15, 52074 Aachen, Germany