Perspective on utilizing foundation models for laboratory automation in materials research

Abstract

This review explores the potential of foundation models to advance laboratory automation in the materials and chemical sciences. We highlight their dual roles within experimental systems, spanning high-level cognitive activities – such as experimental planning, data analysis, and decision-making – and low-level physical operations involving hardware control, sensor integration, and robotic manipulation. While traditional laboratory automation has relied heavily on specialized, rigid systems, foundation models offer adaptability through their general-purpose intelligence and multimodal capabilities. Recent advancements have demonstrated the feasibility of using large language models (LLMs) and multimodal robotic systems to handle complex and dynamic laboratory tasks. However, significant challenges remain, including precision manipulation of hardware, integration of multimodal data, and ensuring operational safety. This paper outlines a roadmap highlighting future directions, advocating for close interdisciplinary collaboration, benchmark establishment, and strategic human-AI integration to realize fully autonomous experimental laboratories.