ExplainabilityTrustworthinessSafetycs.AI
2026 Roadmap on Artificial Intelligence and Machine Learning for Smart Manufacturing
Jay Lee, Hanqi Su, Marco Macchi, Adalberto Polenghi, Wei Wu, Zhiheng Zhao, George Q. Huang, Kiva Allgood, Devendra Jain, Benedikt Gieger, Vibhor Pandhare, Soumyabrata Bhattacharjee, Ram Mohril, Lingbao Kong, Qiyuan Wang, Xinlan Tang, Sungjong Kim, Chan Hee Park, Byeng D. Youn, Guo Dong Goh, Xi Huang, Wai Yee Yeong, Yung C Shin, He Zhang, Zitong Wang, Fei Tao, Jagjit Singh Srai, Satyandra K. Gupta, Byung Gun Joung, Albin John, John W. Sutherland, Sang Won Lee, Olga Fink, Vinay Sharma, Faez Ahmed, Wei Chen, Mark Fuge, Arild Waaler, Martin G. Skjæveland, Dimitris Kyritsis, Wei Chen, VispiNevile Karkaria, Yi-Ping Chen, Ying-Kuan Tsai, Joseph Cohen, Xun Huan, Jing Lin, Liangwei Zhang, Gregory W. Vogl, Aaron W. Cornelius, Xiaodong Jia, Dai-Yan Ji, Takanobu Minami, Ruoxin Wang
April 5, 2026
Machine Learning: Engineering
9 citations
Key Takeaways
-
Data quality and management remain foundational challenges: The roadmap identifies "complexity of industrial big data" and "effective data management" as critical obstacles to AI/ML deployment in manufacturing, suggesting that having more data alone isn't sufficient without proper governance and standardization across industrial systems.
-
Trustworthiness and explainability are essential for high-stakes manufacturing: The paper emphasizes the need for "trustworthy, explainable, and reliable operation in high-stakes industrial environments," indicating that manufacturers cannot simply adopt AI as a black box—they need to understand how AI systems make decisions that could affect safety, quality, and worker welfare.
-
Physics-informed AI represents a responsible path forward: The roadmap highlights "physics-informed AI" as an emerging frontier, suggesting that combining AI with established scientific principles and domain expertise can create more reliable and interpretable systems rather than relying purely on data-driven approaches.
-
Multiple AI approaches are needed for different manufacturing challenges: The roadmap covers diverse applications including robotics, supply chain optimization, digital twins, and sustainable manufacturing, indicating that responsible AI deployment requires tailored solutions rather than one-size-fits-all implementations.
-
Integration across heterogeneous systems is a practical barrier: The paper identifies "integration with heterogeneous sensing and control systems" as a critical challenge, meaning that responsible AI implementation must address real-world complexity where factories use legacy equipment and diverse technologies that weren't designed to work together.