Autonomous multi-robot synthesis and optimization of metal halide perovskite nanocrystals

Abstract

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.

Fig. 1. Schematic illustration of Rainbow’s components and automated functionalities.

a Rainbow is composed of a characterization robot (robot 1), a pipetting robot (robot 2), a robotic arm (robot 3), a labware refreshment robot (robot 4), and an AI agent. Rainbow’s hardware enables automated (i) multi-step synthesis, (ii) sampling, (iii) characterization, and (iv) labware restocking. b A picture of Rainbow’s hardware, including pipetting robot (red), characterization robot (magenta), robotic arm (cyan), and labware refreshment robot (green).

Fig. 2. Selected organic acid ligands’ chemical structures and influences on the synthesis of metal halide perovskite nanocrystals (MHP NCs).

a Chemical structures of a library of organic acid ligands, including butyric acid (C4), hexanoic acid (C6), heptanoic acid (C7), octanoic acid (C8), 2-hexyldecanoic acid (C16), and oleic acid (C18). b The transmission electronic microscopy images and Ultraviolet-visible (UV-Vis) absorption and photoluminescence (PL) spectra along with the photoluminescence quantum yield (PLQY) and full-width-at-half-maximum (FWHM) of the MHP NCs capped by C4, C8, and C18 ligands. The experiments are repeated 3 times to measure the PLQY and FWHM values. Source data are provided as a Source Data file.

Fig. 3. Schematic illustration of Rainbow’s AI agent with inputs and outputs.

a The human scientist defines the target peak emission energy (E_P), objectives, and specifies precursors, followed by b Latin hypercube sampling initialization c experiments. d Rainbow’s AI agent (re)trains the surrogate models, e partitions over the current observations and calculates the current hypervolume (HV) of proxy photoluminescence quantum yield (P_PLQY) and full-width-at-half-maximum (FWHM) at the current target E_P, f samples the feasible parameter space, g performs optimization, h ranks the optimized candidates based on their expected hypervolume improvement (EHVI) and selects the next set of experimental conditions to be tested by Rainbow’s hardware. i The closed-loop experiments output the experimental Pareto-Front, reduction in time-to-solution, metal halide perovskite (MHP) nanocrystal (NC) data/meta library, on-demand synthesis and scalable manufacturing.

Fig. 4. Autonomous Pareto-Front mapping for 1.9 eV peak emission energy (E_P) by Rainbow.

Pictures of well plate under Ultraviolet (UV) illumination of (a) initial conditions generated by Latin hypercube sampling (LHS) and (b) recommended conditions by Bayesian Optimization (BO) towards highest Proxy photoluminescence quantum yield (P_PLQY) and narrowest full-width-at-half-maximum (FWHM) for 1.9 eV E_P. (c) Evolution of P_PLQY vs. FWHM Pareto-Front for 1.9 eV E_P. The experiments followed the arrows’ directions. Source data are provided as a Source Data file.

Fig. 5. Autonomous Pareto-Front mapping for all target peak emission energies (E_Ps) by Rainbow.

Evolution of proxy photoluminescence quantum yield (P_PLQY) vs. full-width-at-half-maximum (FWHM) Pareto-Front for a 1.9 eV, b 2.1 eV, c 2.3 eV, d 2.5 eV, e 2.7 eV, and f 2.9 eV E_P by Latin hypercube sampling (LHS), LHS and 1 iteration of Bayesian Optimization (BO), LHS and 3 BO iterations, LHS and 5 BO iterations. Source data are provided as a Source Data file.

Fig. 6. Ligand structure-synthesis-properties of metal halide perovskite (MHP) nanocrystals (NCs) visualized via Rainbow’s digital twin.

Surface plots presenting the impact of synthesis conditions on a full-width-at-half-maximum (FWHM), b proxy photoluminescence quantum yield (P_PLQY), and c peak emission energy (E_P) of MHP NCs capped by butyric acid (C4); the impact of synthesis conditions on d FWHM, e P_PLQY, and f E_P of MHP NCs capped by oleic acid (C18) for three different normalized concentrations(X) of other parameters listed on the surface plots (low = 0.2, medium = 0.5, and high = 0.8) with respect to their dosage upper limit. Source data are provided as a Source Data file.

Fig. 7. Knowledge scalability of Rainbow synthesis.

Comparisons of Ultraviolet-visible (UV-Vis) absorption (abs) and photoluminescence (PL) spectra between autonomous (Rainbow) and scaled-up synthesis of the best-performing metal halide perovskite (MHP) nanocrystals (NCs) for all target E_Ps values of a 1,9 eV, b 2.1 eV, c 2.3 eV, d 2.5 eV, e 2.7 eV, and f 2.9 eV. The inserts show the pictures of scaled-up MHP NC synthesis products under UV illumination. Source data are provided as a Source Data file.