Toward autonomous laboratories: Convergence of artificial intelligence and experimental automation

The ever-increasing demand for novel materials with superior properties inspires retrofitting traditional research paradigms in the era of artificial intelligence and automation. An autonomous experimental platform (AEP) has emerged as an exciting research frontier that achieves full au-tonomy via integrating data-driven algorithms such as machine learning (ML) with experimental automation in the material development loop from synthesis, characterization, and analysis, to decision making. In this review, we started with a primer to describe how to develop data-driven algorithms for solving material problems. Then, we systematically summarized recent progress on automated material synthesis, ML-enabled data analysis, and decision-making. Finally, we dis-cussed the challenges and opportunities in an endeavor to develop the next-generation AEP for ultimately realizing an autonomous or self-driving laboratory. This review will provide insights for researchers aiming to learn the frontier of ML in materials science and deploy AEP in their labs for accelerating material development.

Automated summary

The increasing demand for novel materials has led to the retrofitting of traditional research paradigms with artificial intelligence and automation. An autonomous experimental platform (AEP) has emerged as a research frontier that integrates data-driven algorithms and experimental automation for material development. This review provides insights into developing data-driven algorithms, recent progress in automated material synthesis, ML-enabled data analysis, and decision-making, and the challenges and opportunities in developing the next-generation AEP for autonomous laboratories.