Kim, Youhyun Doo, Hayoung Shin, Daeun Lee, Seo Yoon Roh, Yugyeong Park, Seongeun Song, Heejin Jung, Yujin Yoo, Hyuk Jun Han, Sang Soo Kim, Jong Woo Besenhard, Maximilian O. Lee, Ye Seol Na, Jonggeol 2025-11-13T08:06:31Z 2025-11-13T08:06:31Z 2025-11-11 2025-12 0098-1354 https://pubs.kist.re.kr/handle/201004/153443 Self-driving laboratories (SDLs), also known as autonomous laboratories, have recently gained in popularity due to their rapid advances in hardware for solving real-world problems and connectivity with various artificial intelligence (AI) embedded software. SDLs with autonomy have the potential to accelerate the development in chemistry and materials science, which leads to solving design problems that are difficult for human intuition. The concept of SDLs is quite similar to that of process automation and AI-enabled autonomy in chemical engineering, which are current focused research topics in process systems engineering (PSE). However, SDLs have lacked discussion from this perspective, although they require the artistic integration of technologies such as optimization, process monitoring, product and process design, control, and machine learning, which are traditionally studied by the PSE discipline. Here, we discuss the importance of PSE in improving key SDL technologies. We first provide an overview of process integration with various types of hardware for SDLs that each experimental hardware component in the laboratory must be automated to enable autonomy. Most importantly, this review conducts a deep dive into how software can be applied to enhance and actualize SDLs, which is highly related to the implications and opportunities for PSE researchers studying SDL-specific operating systems, optimization algorithms for SDLs-generated chemicals and materials, and use of AI to achieve system-wide autonomy. English Pergamon Press Ltd. Self-driving laboratories with artificial intelligence: An overview of process systems engineering perspective Article 10.1016/j.compchemeng.2025.109266 1 Computers & Chemical Engineering, v.203 Computers & Chemical Engineering 203 N scie scopus 001582215400001 2-s2.0-105012735488 Computer Science, Interdisciplinary Applications Engineering, Chemical Computer Science Engineering Article CONSTRAINED BAYESIAN OPTIMIZATION HIGH-THROUGHPUT EXPERIMENTATION DERIVATIVE-FREE OPTIMIZATION AIDED MOLECULAR DESIGN WORKING-FLUID FAULT-DETECTION MULTIOBJECTIVE OPTIMIZATION AUTOMATED OPTIMIZATION INTEGRATED SOLVENT LEARNING-METHODS Self-driving laboratory Process systems engineering Artificial intelligence Optimization Autonomous discovery Process and product design