Aligning an optical interferometer with beam divergence control and continuous action space
Reinforcement learning is finding its way to real-world problem application, transferring from simulated environments to physical setups. In this work, we implement vision-based alignment of an optical Mach-Zehnder interferometer with a confocal telescope in one arm, which controls the diameter and divergence of the corresponding beam. We use a continuous action space; exponential scaling enables us to handle actions within a range of over two orders of magnitude. Our agent trains only in a simulated environment with domain randomizations. In an experimental evaluation, the agent significantly outperforms an existing solution and a human expert.
Code (1)
Tasks
reinforcement-learningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Leveraging machine learning features for linear optical interferometer control
We have developed an algorithm that constructs a model of a reconfigurable optical interferometer, independent of specific architectural constraints. The programming of unitary transformations on the interferometer's opt…
Interferobot: aligning an optical interferometer by a reinforcement learning agent
Limitations in acquiring training data restrict potential applications of deep reinforcement learning (RL) methods to the training of real-world robots. Here we train an RL agent to align a Mach-Zehnder interferometer, w…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Prototype Development and Validation of a Beam-Divergence Control System for Free-Space Laser Communications
Being able to dynamically control the transmitted-beam divergence can bring important advantages in free-space optical communications. Specifically, this technique can help to optimize the overall communications performa…
Beam with Adaptive Divergence Angle in Free-Space Optical Communications for High-Speed Trains
In this paper, we propose an adaptive beam that adapts its divergence angle according to the receiver aperture diameter and the communication distance to improve the received power and ease the alignment between the comm…
Iso-propagation vortices with OAM-independent size and divergence toward future faster optical communications
Recognized in the 1990s, vortex beams’ ability to carry orbital angular momentum (OAM) has significantly contributed to applications in optical manipulation and high-dimensional classical and quantum information commun…