Autonomous Diffractometry Enabled by Visual Reinforcement Learning
2026-04-13 • Machine Learning
Machine LearningComputer Vision and Pattern Recognition
AI summaryⓘ
The authors created a computer system that can automatically align single crystals by looking at their diffraction patterns, without needing to understand the underlying science of crystallography. Their system uses a type of machine learning called reinforcement learning, where the computer learns by itself to find the best crystal orientations. The computer figures out strategies similar to those used by humans, making the alignment process quicker and efficient. This work helps make experiments in materials science more automated and less reliant on expert human input.
automationsingle crystalsLaue diffractionreinforcement learningcrystal alignmentdiffraction patternscrystallographymaterials scienceexperimental workflows
Authors
J. Oppliger, M. Stifter, A. Rüegg, I. Biało, L. Martinelli, P. G. Freeman, D. Prabhakaran, J. Zhao, Q. Wang, J. Chang
Abstract
Automation underpins progress across scientific and industrial disciplines. Yet, automating tasks requiring interpretation of abstract visual information remain challenging. For example, crystal alignment strongly relies on humans with the ability to comprehend diffraction patterns. Here we introduce an autonomous system that aligns single crystals without access to crystallography and diffraction theory. Using a model-free reinforcement learning framework, an agent learns to identify and navigate towards high-symmetry orientations directly from Laue diffraction patterns. Despite the absence of human supervision, the agent develops human-like strategies to achieve time-efficient alignment across different crystal symmetry classes. With this, we provide a computational framework for intelligent diffractometers. As such, our approach advances the development of automated experimental workflows in materials science.