2026-11-05 物質・材料研究機構

図: NIMOによるAIと実験の連携。手作業の実験(上)と自動・自律実験(下)の双方で、実験結果を次の条件提案に反映します。
<関連情報>
- https://www.nims.go.jp/press/2026/11/202611050.html
- https://pubs.rsc.org/dd/article/doi/10.1039/d6dd00371k/1377109/NIMO-a-software-platform-for-closed-loop-materials
NIMO:多様なAIアルゴリズムを用いたクローズドループ型材料探索のためのソフトウェアプラットフォーム
NIMO: a software platform for closed-loop materials exploration with diverse AI algorithms
Ryo Tamura; Naruki Yoshikawa; Koji Tsuda; Shoichi Matsuda
Digital Discovery Published:19 October 2026
DOI:https://doi.org/10.1039/d6dd00371k
Self-driving laboratories (SDLs), where artificial intelligence proposes subsequent experiments and robotic systems execute them, are rapidly becoming an important approach to autonomous materials exploration. A practical challenge lies in connecting AI algorithms for different exploration goals with heterogeneous experimental hardware and control software. Here, we provide a perspective on NIMO, an open-source software platform that addresses this challenge through three core paradigms: a modular AI-robot decoupling mediated via simple CSV file exchange, a discrete candidate-pool architecture that incorporates domain knowledge, and a unified Python interface providing access to twelve distinct AI algorithms. In this perspective, we review the operational principles of each algorithm alongside six diverse SDL implementations driven by NIMO, covering electrolyte discovery, organic synthesis, thin-film exploration, fuel-cell process informatics, coffee-ring phase exploration, and legacy liquid-handling automation. One of these also demonstrates NIMO’s interoperability with the IvoryOS orchestration framework. To democratize autonomous science, we also introduce a no-code desktop application that enables intuitive, human-in-the-loop exploration for non-programmers. NIMO is freely available at https://github.com/NIMS-DA/nimo.


