Xu Jinge, Moran Christopher H J, Ghorai Arup, Bateni Fazel, Bennett Jeffrey A, Mukhin Nikolai, Latif Koray, Cahn Andrew, Jha Pragyan, Licona Fernando Delgado, Sadeghi Sina, Politi Lior, Abolhasani Milad
Department of Chemical and Biomolecular Engineering, North Carolina State University, Raleigh, NC, USA.
Department of Computer Science, North Carolina State University, Raleigh, NC, USA.
Nat Commun. 2025 Aug 22;16(1):7841. doi: 10.1038/s41467-025-63209-4.
Metal halide perovskite (MHP) nanocrystals (NCs) offer extraordinary tunability in their optical properties, yet fully exploiting this potential is challenged by a vast and complex synthesis parameter space. Herein, we introduce Rainbow, a multi-robot self-driving laboratory that integrates automated NC synthesis, real-time characterization, and machine learning (ML)-driven decision-making to efficiently navigate MHP NCs' mixed-variable high-dimensional landscape. Using parallelized, miniaturized batch reactors, robotic sample handling, and continuous spectroscopic feedback, Rainbow autonomously optimizes MHP NC optical performance-including photoluminescence quantum yield and emission linewidth at a targeted emission energy-through closed-loop experimentation. By systematically exploring varying ligand structures and precursor conditions, Rainbow elucidates critical structure-property relationships and identifies scalable Pareto-optimal formulations for targeted spectral outputs. Rainbow provides a versatile blueprint for accelerated, data-driven discovery and retrosynthesis of high-performance metal halide perovskite nanocrystals, facilitating the on-demand realization of next-generation photonic materials and technologies.
金属卤化物钙钛矿（MHP）纳米晶体（NCs）在光学性质方面具有非凡的可调性，然而，要充分挖掘这一潜力却面临着庞大而复杂的合成参数空间的挑战。在此，我们介绍Rainbow，这是一个多机器人自动驾驶实验室，它集成了自动化的纳米晶体合成、实时表征以及机器学习（ML）驱动的决策，以有效地探索MHP纳米晶体的混合变量高维空间。Rainbow利用并行化、小型化的间歇式反应器、机器人样品处理以及连续光谱反馈，通过闭环实验自主优化MHP纳米晶体的光学性能，包括在目标发射能量下的光致发光量子产率和发射线宽。通过系统地探索不同的配体结构和前驱体条件，Rainbow阐明了关键的结构-性质关系，并确定了针对目标光谱输出的可扩展帕累托最优配方。Rainbow为高性能金属卤化物钙钛矿纳米晶体的加速、数据驱动的发现和逆合成提供了一个通用蓝图，有助于按需实现下一代光子材料和技术。
