Automating Experimental Optics with Sample Efficient Machine Learning Methods
Preprint
Abstract
As free-space optical systems grow in scale and complexity, troubleshooting becomes increasingly time-consuming and, in the case of remote installations, perhaps impractical. An example of a task that is often laborious is the alignment of a high-finesse optical resonator, which is highly sensitive to the mode of the input beam. In this work, we demonstrate how machine learning can be used to achieve autonomous mode-matching of a free-space optical resonator with minimal supervision. Our approach leverages sample-efficient algorithms to reduce data requirements while maintaining a simple architecture for easy deployment. The reinforcement learning scheme that we have developed shows that automation is feasible even in systems prone to drift in experimental parameters, as may well be the case in real-world applications.Keywords
All Related Versions
This publication has 38 references indexed in Scilit:
- Quantum sensing with optically accessible spin defects in van der Waals layered materialsLight: Science & Applications, 2024
- A review of automation of laser optics alignment with a focus on machine learning applicationsOptics and Lasers in Engineering, 2023
- Challenges of real-world reinforcement learning: definitions, benchmarks and analysisMachine Learning, 2021
- Control of Stepper Motor Rotary Stages applied to optical sensing technique using LabViewOptik, 2018
- Ensemble learning: A surveyWIREs Data Mining and Knowledge Discovery, 2018
- Satellite-to-ground quantum-limited communication using a 50-kg-class microsatelliteNature Photonics, 2017
- Photonic quantum technologiesNature Photonics, 2009
- Automatic alignment of a rigid spacer cavityGeneral Relativity and Gravitation, 2005
- An automatic fiber alignment system using genetic algorithmsSystems and Computers in Japan, 2004
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989