Material intelligence by the convergence of artificial intelligence and robotic platforms
Xinyu Zhang, Zijian Chen, Feibei Chen, Billy Fanady, Bo-Yuan Wang, Zongming Ni, Shumin Zhou, Junzhi Ye, Guanhua Chen, Jie Liu, Robert L. Z. Hoye, Xiaobo Li, Samantha Y. Chong, Wei Feng, Chi-yung Chung, Ching-chuen Chan, Linjiang Chen, Han Hao, Alán Aspuru‐Guzik, Jun Jiang, Haitao Zhao
Abstract
The emerging interdisciplinary research of material intelligence through the convergence of artificial intelligence, robotic platforms, and material informatics has revolutionized the field of chemistry and material science. This shift enables precision and intelligence in materials research to avoid the problems of trial-and-error synthesis and labor-intensive characterization. The aim of this review is to present a comprehensive methodology that unifies three interlinked domains: data-guided rational design ("reading"), automation-enabled controllable synthesis ("doing"), and autonomy-facilitated inverse design ("thinking"). We critically examine how the integration of materials common discipline (i.e., rational design, controllable synthesis, inverse design) with interdisciplinary research (i.e., data, automation, autonomy), with an emphasis on cutting-edge research of artificial intelligence and robotics, collectively shape a closed-loop next paradigm of material intelligence, revolutionizing experimental, theoretical, software-driven and data-driven paradigms. Ultimately, this paper discusses how these insights drive the new paradigm of materials research, which seamlessly combines database, robotics, artificial intelligence, and even embodied intelligence to empower the full potential of material intelligence.