ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization

2024-01-13

Matter

AI Summary

Chemical experiments are typically time-consuming, physically demanding, highly repetitive, and involve complex decision-making. To address these challenges, we introduce ORGANA, an intelligent robotic assistant for chemical laboratories, which pioneers the “Chemist-in-the-Loop” paradigm. ORGANA integrates large language model (LLM)-driven semantic understanding, vision-feedback-guided task planning, and multi-device coordinated control to enable closed-loop execution and human–robot collaborative decision-making across diverse tasks—including solubility determination, pH measurement, recrystallization, and electrochemical characterization. The system dynamically resolves ambiguities, schedules parallel multi-step operations, and interfaces with laboratory equipment via standardized APIs and motion-control modules. In a benchmark electrochemical characterization task on quinone derivatives, ORGANA executed 19 concurrent experimental steps, reducing user time by 80.3% and decreasing perceived frustration and physical workload by over 50%.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Natural Language Processing: Safety and Robustness
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

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.

Problem

• Chemical Experiment Efficiency
• Labor Intensity
• Complex Repetitive Operations

Innovation

• AutomatedChemicalExperiments
• VisualRecognition
• LanguageModelIntegration