ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization

TL;DR

ORGANA is an innovative robotic system that automates complex chemistry experiments, integrating decision-making, perception, and natural language interaction to enhance efficiency and reduce manual effort in laboratory settings.

Contribution

This paper introduces ORGANA, a novel robotic platform that combines LLMs, visual feedback, and automation to perform diverse chemistry experiments with minimal human intervention.

Findings

Successfully automated electrochemistry experiments with 19-step plans.

Reduced user frustration and physical effort by over 50%.

Users saved an average of 80.3% of their time using ORGANA.

Abstract

Chemistry experiments can be resource- and labor-intensive, often requiring manual tasks like polishing electrodes in electrochemistry. Traditional lab automation infrastructure faces challenges adapting to new experiments. To address this, we introduce ORGANA, an assistive robotic system that automates diverse chemistry experiments using decision-making and perception tools. It makes decisions with chemists in the loop to control robots and lab devices. ORGANA interacts with chemists using Large Language Models (LLMs) to derive experiment goals, handle disambiguation, and provide experiment logs. ORGANA plans and executes complex tasks with visual feedback, while supporting scheduling and parallel task execution. We demonstrate ORGANA's capabilities in solubility, pH measurement, recrystallization, and electrochemistry experiments. In electrochemistry, it executes a 19-step plan in parallel to characterize quinone derivatives for flow batteries. Our user study shows ORGANA reduces frustration and physical demand by over 50%, with users saving an average of 80.3% of their time when using it.