Human-AI collaborative autonomous synthesis with pulsed laser deposition for remote epitaxy
This work addresses the problem of inefficient autonomous synthesis in materials science by enhancing human-AI collaboration, though it is incremental as it builds on existing human-in-the-loop workflows.
The researchers tackled the challenge of optimizing remote epitaxy of BaTiO3/graphene using pulsed laser deposition by developing a human-AI collaborative workflow, which accelerated hypothesis formation and experimental design, identifying a low-O2 pressure low-temperature synthesis window that preserves graphene but requires a two-step Ar/O2 deposition for optimal BaTiO3 growth.
Autonomous laboratories typically rely on data-driven decision-making, occasionally with human-in-the-loop oversight to inject domain expertise. Fully leveraging AI agents, however, requires tightly coupled, collaborative workflows spanning hypothesis generation, experimental planning, execution, and interpretation. To address this, we develop and deploy a human-AI collaborative (HAIC) workflow that integrates large language models for hypothesis generation and analysis, with collaborative policy updates driving autonomous pulsed laser deposition (PLD) experiments for remote epitaxy of BaTiO$_3$/graphene. HAIC accelerated the hypothesis formation and experimental design and efficiently mapped the growth space to graphene-damage. In situ Raman spectroscopy reveals that chemistry drives degradation while the highest energy plume components seed defects, identifying a low-O$_2$ pressure low-temperature synthesis window that preserves graphene but is incompatible with optimal BaTiO$_3$ growth. Thus, we show a two-step Ar/O$_2$ deposition is required to exfoliate ferroelectric BaTiO$_3$ while maintaining a monolayer graphene interlayer. HAIC stages human insight with AI reasoning between autonomous batches to drive rapid scientific progress, providing an evolution to many existing human-in-the-loop autonomous workflows.