Autonomous Diffractometry Enabled by Visual Reinforcement Learning

TL;DR

This paper presents an autonomous, reinforcement learning-based system that aligns crystals using diffraction patterns without human supervision, advancing automated materials science workflows.

Contribution

It introduces a model-free reinforcement learning approach enabling autonomous crystal alignment directly from diffraction images, bypassing traditional crystallography methods.

Findings

Agent learns to identify high-symmetry orientations from diffraction patterns.

System achieves time-efficient alignment across various crystal symmetries.

Develops human-like strategies for crystal alignment without supervision.

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.