Self-driving laboratories integrate artificial intelligence, robotic automation, and high-throughput characterisation into closed-loop experimental workflows that are reshaping how energy materials are discovered. This symposium brings together leading practitioners advancing self-driving laboratories for energy and energy-related applications, including photovoltaics, batteries and electrochemical storage, electrocatalysis and photocatalysis for fuels and chemicals, hydrogen production, and the recovery of critical minerals that underpin the energy transition. The unifying questions are methodological: how do Bayesian optimisation, active learning, and foundation model driven planning transfer across forward synthesis and inverse recovery problems; how should the community benchmark closed-loop performance fairly across distinct workflows; and how can large language model agents and shared digital infrastructure accelerate discovery beyond any single laboratory. We invite contributions spanning autonomous experimentation platforms, physics informed machine learning, mobile robotic chemists, flexible automation, and human-AI collaboration in the pursuit of a sustainable energy economy. The symposium will foster dialogue between academic, government laboratory, and industrial researchers driving the next generation of accelerated materials discovery.
- Self-driving laboratories and closed-loop discovery
- AI-accelerated photovoltaic materials and devices
- Autonomous discovery of battery and electrochemical storage materials
- Machine learning for electrocatalysis, photocatalysis, and solar fuels
- Mobile robotic chemists and flexible laboratory automation
- Bayesian optimisation, active learning, and small-data machine learning
- Foundation models and LLM agents for autonomous experimentation
- Sustainable and bio-derived materials for the energy transition
- Critical mineral recovery and circular energy materials
- Benchmarking, reproducibility, and digital infrastructure for SDLs
Don N. Futaba is a Principal Researcher at the National Institute of Advanced Industrial Science and Technology (AIST) in Tsukuba, Japan. He received his B.A. in Physics from the University of California, Berkeley, and his Ph.D. in Physics from the University of California, Davis. He joined AIST in 2004, where he began research on carbon nanotube (CNT) synthesis under Prof. Sumio Iijima and developed the water-assisted CVD (“super-growth”) method for high-yield CNT forest synthesis.
His research has evolved from CNT synthesis, characterization, and scale-up toward the broader study of complex materials processes and how they can be better understood, controlled, and investigated. His current work combines data-driven analysis, perturbation-based approaches, AI-assisted scientific reasoning, and autonomous experimentation to uncover process behavior and accelerate scientific discovery. In parallel, he is involved in developing autonomous research systems and knowledge frameworks that enable experimental capabilities and experience to be shared and reused. CNT synthesis serves both as an important model system for this research and as a pathway for translating fundamental understanding into industrial technology.
His research has contributed to the industrial-scale production of CNTs and has resulted in more than 130 peer-reviewed publications and over 60 domestic and international patents. His honors include the 2016 MEXT Commendation for Science and Technology, the 2016 21st Century Invention Incentive Award and 21st Century Invention Contribution Award from the Japan Institute of Invention and Innovation, and the 2019 AIST President Award.
Leonard Ng Wei Tat is an Assistant Professor at the School of Materials Science and Engineering, Nanyang Technological University (NTU), Singapore, a Cluster Director at the Energy Research Institute @ NTU (ERI@N), PI at TUMCreate’s Proteins4Singapore project and deputy director of the AI for Materials Initiative (AIM). He leads the NGenuity Lab, a multidisciplinary research group of approximately eleven researchers working at the intersection of artificial intelligence, automation, and advanced materials. His research focuses on self-driving laboratories for accelerated materials discovery, AI-driven optimisation of photovoltaic devices (perovskite and organic solar cells), autonomous hydrometallurgical processing of e-waste, biomaterial scaffold design for cultivated meat and protein extraction from alternative protein sources such as soybean and microalgae. Leonard obtained his PhD in Engineering from the University of Cambridge, an MSc in Materials Science from the University of Leeds, a BSc in Political Science from Singapore Management University, and an MSc in Computer Science from Georgia Institute of Technology. He is a Member of the Royal Society of Chemistry (MRSC).