Status of Accelerator Automation in the Community: Classification, Survey Results, and the Role of AI and Machine Learning
Abstract
The increasing complexity of particle accelerators and the growing demand for operational efficiency have intensified the focus on automation in accelerator control systems. However, there is still a lack of a common language to describe and compare the level of automation across different facilities. This article presents a generic classification scheme for accelerator automation, defining five distinct levels ranging from basic operational assistance to full autonomy. To assess the current state of automation in the accelerator community, a structured survey was conducted during the 14th Workshop on Accelerator Operations (WAO 2025). Responses from major laboratories indicate that more than one third of accelerators currently operate at the lowest level 1 (operational assistance), and no facility has yet reached full automation. However, projections show a clear trend toward higher levels within the next decade. Key drivers include optimization algorithms for autotuning, finite-state machines, and closed-loop feedback systems. This study provides both a conceptual framework and a snapshot of current implementation practices, supporting a shared understanding of accelerator automation across the community.
Related
- Reinforcement Learning in High-Energy Physics: A Survey from Accelerator Control to Theory Exploration
- Linac performance benchmarking: Feasibility of a web-based tool for comparison of local machine performance check (MPC) results with the global community.
- Failure classification of wind turbine operational conditions using hybrid machine learning
- Test beam results for machine-learning-based reconstruction of resistive silicon sensors
- A Workshop Series for Effective Use of AI in Uncertain Times: Building a Physics Faculty Learning Community
BibTeX
@misc{reimann2026status,
title = {{Status of Accelerator Automation in the Community: Classification, Survey Results, and the Role of AI and Machine Learning}},
author = {S. Reimann and F. Miyahara and M. Lafky and P. Schuh and J. Xing and G. Johns and R. Steerenberg and B. Freeman and K. Genge and M. Pont and G. Marr and Y. Iwata and L. Hardy},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.10835},
eprint = {2611.10835},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.10835},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Status of Accelerator Automation in the Community: Classification, Survey Results, and the Role of AI and Machine Learning
AU - S. Reimann
AU - F. Miyahara
AU - M. Lafky
AU - P. Schuh
AU - J. Xing
AU - G. Johns
AU - R. Steerenberg
AU - B. Freeman
AU - K. Genge
AU - M. Pont
AU - G. Marr
AU - Y. Iwata
AU - L. Hardy
PY - 2026
DA - 2026/11/07
PB - arXiv
DO - 10.48550/arxiv.2611.10835
UR - https://arxiv.org/abs/2611.10835
AB - The increasing complexity of particle accelerators and the growing demand for operational efficiency have intensified the focus on automation in accelerator control systems. However, there is still a lack of a common language to describe and compare the level of automation across different facilities. This article presents a generic classification scheme for accelerator automation, defining five distinct levels ranging from basic operational assistance to full autonomy. To assess the current state of automation in the accelerator community, a structured survey was conducted during the 14th Workshop on Accelerator Operations (WAO 2025). Responses from major laboratories indicate that more than one third of accelerators currently operate at the lowest level 1 (operational assistance), and no facility has yet reached full automation. However, projections show a clear trend toward higher levels within the next decade. Key drivers include optimization algorithms for autotuning, finite-state machines, and closed-loop feedback systems. This study provides both a conceptual framework and a snapshot of current implementation practices, supporting a shared understanding of accelerator automation across the community.
ER -