Self-driving AMADAP laboratory: Accelerating the discovery and optimization of emerging perovskite photovoltaics

Abstract The development of new solar materials for emerging perovskite photovoltaics poses intricate multi-objective optimization challenges in a large high-dimensional composition and parameter space, with in some cases, millions of potential candidates to be explored. Solving it necessitates reproducible, user-independent laboratory work and intelligent preselection of innovative experimental methods. Materials Acceleration Platforms (MAPs) seamlessly combine robotic materials synthesis, characterization, and AI-driven data analysis, enabling the exploration of new materials. They revolutionize material development by replacing trial-and-error methods with precise, rapid experimentation and generating high-quality data for training machine learning (ML) algorithms. Device Acceleration Platforms (DAPs) focus on optimizing functional energy films and multilayer stacks. Unlike MAPs, DAPs concentrate on refining processing conditions for predetermined materials, crucial for disordered semiconductors. By fine-tuning processing parameters, DAPs significantly advance disordered semiconductor devices such as emerging photovoltaics. This article examines recent advancements in automated laboratories for perovskite material discovery and photovoltaics device optimization, showcasing in-house-developed MAPs and a DAP. These platforms cover the entire value chain, from materials to devices, addressing optimization challenges through robot-based high-throughput experimentation (HTE). Ultimately, a self-driven Autonomous Material and Device Acceleration Platforms (AMADAP) laboratory concept is proposed for autonomous functional solar material discovery using AI-guided combinational approaches. Graphical abstract