CRESt – Copilot for Real-world Experimental Scientist

Abstract

Autonomous laboratories were previously controlled mainly by scripting languages such as Python, limiting their usage among experimentalists. The recent release of OpenAI's ChatGPT API's function calling feature has enabled seamless integration and execution of Python subroutines in experimental workflows using voice commands. We have developed a system of Copilot for Real-world Experimental Scientist (CRESt) system, with a demonstration shown on YouTube. Large language models (LLMs) empower all research group members, regardless of coding experience, to leverage the robotic platform for their own projects, simply by talking with CRESt.