Tetsuya Asai

Yuito Ito, Anas Skalli, Tetsuya Asai et al.

Physical reservoir computing has traditionally exploited the dynamics of physical systems for computation, enabling tasks such as inference, classification, and prediction. Here, we introduce a fundamentally different paradigm for exploiting physical reservoirs, termed "reservoir signal acquisition" (RSA), in which a physical reservoir serves as a dynamical measurement device rather than a computational engine. In RSA, the reservoir transforms an unknown broadband waveform into a diverse set of measurements, enabling waveform reconstruction from low-rate samples beyond the Nyquist limit of any individual acquisition channel. We show that exact reconstruction of arbitrary broadband signals is achieved when the number of measurement channels satisfies $M \geq N_R$, where $N_R$ is the undersampling ratio. Moreover, spectrally or temporally sparse signals can be recovered even when $M \ll N_R$, demonstrating a compressed-sensing capability that naturally emerges from the diversity of reservoir dynamics. We experimentally validate RSA using a silicon photonic reservoir circuit. With a data-driven calibration requiring no physical model of the device, we reconstruct radio-frequency signals up to 12.5 GHz using only low-rate analog-to-digital converters (ADCs), corresponding to four times the Nyquist frequency of each ADC. These results establish RSA as a new signal acquisition paradigm based on physical reservoirs, extending their role from computation to sub-Nyquist acquisition of broadband waveforms.

Akira Miura, Yuki Sasahara, Momoka Demura et al.

Advances in Materials Informatics have accelerated the development of Self-Driving Laboratories (SDLs), yet human-led experiments remain standard in many educational and exploratory research settings. In such environments, practical know-how, including operational details and site-specific rules, is essential for safe and reliable laboratory work. In this proof-of-concept study, we developed a human-in-the-loop AI assistant that combines first-person experimental video, multimodal AI, and retrieval-augmented generation (RAG). Using powder X-ray diffraction experiments and student-recorded video data as inputs, the system extracts site-specific laboratory knowledge from recorded procedures, including physical techniques and audible confirmation that conventional manuals could omit. It then provides grounded responses based on the resulting manual. To reduce the risk of unsupported outputs, the system employs a two-layer safety design: source restriction through RAG and strict system-prompt constraints. Instructor-based evaluation showed alignment with expected guidance for questions covered by the manual. For out-of-scope queries, the system appropriately refused to answer, indicating a reduced risk of hallucination. Expert evaluation further indicated that the generated advisory reports were useful and safe (utility: 3.25/4.00; safety: 4.00/4.00). These results suggest a framework in which AI supports laboratory practice under explicit human supervision rather than replacing human judgment.