TARMAC: A Taxonomy for Robot Manipulation in Chemistry

2025-10-22

AI Summary

Chemical laboratory automation remains heavily reliant on human intervention, primarily due to the absence of standardized representations for robotic manipulation skills—resulting in highly task-specific, non-generalizable solutions. To address this, we propose TARMAC, the first robot action classification framework tailored for chemical experimentation. TARMAC introduces a novel dual-dimensional taxonomy—“functional role” and “physical execution”—enabling reusable, composable skill representations spanning atomic actions to macro-level experimental workflows. Grounded in expert-annotated teaching-lab data, the framework instantiates operations as robot-executable primitives and supports high-level instruction orchestration. Experimental evaluation demonstrates that TARMAC significantly enhances integration capability for long-duration experimental protocols and improves system autonomy. By establishing a scalable, standardized foundation for chemical robotics, TARMAC bridges the gap between domain-specific chemistry knowledge and general-purpose robotic control.

Technology Category

• Intelligent Robots: Manipulation
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Knowledge Representation and Reasoning: Automated Reasoning and Theorem Proving

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Chemistry laboratory automation aims to increase throughput, reproducibility, and safety, yet many existing systems still depend on frequent human intervention. Advances in robotics have reduced this dependency, but without a structured representation of the required skills, autonomy remains limited to bespoke, task-specific solutions with little capacity to transfer beyond their initial design. Current experiment abstractions typically describe protocol-level steps without specifying the robotic actions needed to execute them. This highlights the lack of a systematic account of the manipulation skills required for robots in chemistry laboratories. To address this gap, we introduce TARMAC - a Taxonomy for Robot Manipulation in Chemistry - a domain-specific framework that defines and organizes the core manipulations needed in laboratory practice. Based on annotated teaching-lab demonstrations and supported by experimental validation, TARMAC categorizes actions according to their functional role and physical execution requirements. Beyond serving as a descriptive vocabulary, TARMAC can be instantiated as robot-executable primitives and composed into higher-level macros, enabling skill reuse and supporting scalable integration into long-horizon workflows. These contributions provide a structured foundation for more flexible and autonomous laboratory automation. More information is available at https://tarmac-paper.github.io/

Problem

• Developing a structured taxonomy for robotic manipulation skills in chemistry labs
• Addressing the lack of systematic representation for robot actions in experiments
• Enabling skill reuse and scalable integration in laboratory automation workflows

Innovation

• Introduces TARMAC taxonomy for robot manipulation skills
• Categorizes actions by functional role and execution requirements
• Enables skill reuse via robot-executable primitives and macros