Machine Learning based Pointing Stabilization for Low-Repetition-Rate High Power Lasers
A novel machine-learning based closed-loop control system to enhance spatial transverse stability of high-power lasers, overcoming the bandwidth limitations of traditional feedback systems. Tested at the BELLA Center, it achieved sub- µrad stability, marking the first successful predictive control in high-power low-repetition-rate facility.
Authors
- Alessio Amodio
- A. Picksley (ORCID: https://orcid.org/0000-0002-5334-1509)
- Mahek Logantha
- A. J. Gonsalves (ORCID: https://orcid.org/0000-0002-2567-7582)
- Russell Wilcox
- Dan Wang
- Qing Ji (ORCID: https://orcid.org/0000-0001-6576-9142)
- Hai-En Tsai (ORCID: https://orcid.org/0000-0002-8667-5468)
- Curtis J. Berger (ORCID: https://orcid.org/0000-0003-3061-2406)
- Qiang Du (ORCID: https://orcid.org/0000-0002-2196-9801)
- Zachary Eisentraut
- Samuel K. Barber
- Jeroen van Tilborg
- Neel Rajeshbhai Vora
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1364/cleo_at.2025.aa113_5
- Primary Topic
- Laser Material Processing Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00