Summary
NTT says its autonomous deposition system accelerated the experiment cycle by about three times and produced a high-quality single-crystal beta-gallium-oxide film using sputtering. The system combines robotic substrate handling, automated optical measurement and Bayesian optimisation, with the stated goal of turning black-box search into transferable scientific knowledge.
Why it matters
The demonstration connects AI agents to laboratory equipment and shows how physical experimentation can be accelerated while preserving human-readable explanations of the resulting process.
Related coverage
- Accelerated Understanding unveils a non-Transformer physics AI
- Generalist raises another $200 million for robot foundation models
- Nvidia doubles entry-level edge compute with Jetson Orin Nano 2