Toward Full Autonomous Laboratory Instrumentation Control with Large Language Models
For researchers lacking programming skills, this work shows that LLMs can lower the barrier to automating complex lab instruments, but the results are preliminary and incremental.
This work demonstrates that LLMs like ChatGPT can enable non-expert researchers to program and automate laboratory instruments, reducing the technical barrier. In a case study, ChatGPT facilitated script creation for a single-pixel camera/scanning photocurrent microscope, and autonomous AI agents were shown to independently operate instruments and refine control strategies.
The control of complex laboratory instrumentation often requires significant programming expertise, creating a barrier for researchers lacking computational skills. This work explores the potential of large language models (LLMs), such as ChatGPT, and LLM-based artificial intelligence (AI) agents to enable efficient programming and automation of scientific equipment. Through a case study involving the implementation of a setup that can be used as a single-pixel camera or a scanning photocurrent microscope, we demonstrate how ChatGPT can facilitate the creation of custom scripts for instrumentation control, significantly reducing the technical barrier for experimental customization. Building on this capability, we further illustrate how LLM-assisted tools can be extended into autonomous AI agents capable of independently operating laboratory instruments and iteratively refining control strategies. This approach underscores the transformative role of LLM-based tools and AI agents in democratizing laboratory automation and accelerating scientific progress.