Chemistry

A dynamic knowledge graph approach to distributed self-driving laboratories

J. Bai, S. Mosbach, et al.

Dive into the innovative architecture for distributed self-driving laboratories developed by Jiaru Bai, Sebastian Mosbach, Connor J. Taylor, and their team. This research showcases a dynamic knowledge graph that radically enhances design-make-test-analyze cycles through autonomous agents, culminating in a remarkable closed-loop optimization for an aldol condensation reaction across continents in just three days.

00:00

Playback language: English

Index

Abstract

This work develops an architecture for distributed self-driving laboratories (SDLs) within The World Avatar project, using a dynamic knowledge graph. Ontologies capture data and material flows in design-make-test-analyse cycles, with autonomous agents executing the workflow. Data provenance is meticulously recorded. A collaborative closed-loop optimization for an aldol condensation reaction is demonstrated using robots in Cambridge and Singapore, generating a Pareto front for cost-yield optimization in three days.

Publisher

Nature Communications

Published On

Jan 23, 2024

Authors

Jiaru Bai, Sebastian Mosbach, Connor J. Taylor, Dogancan Karan, Kok Foong Lee, Simon D. Rihm, Jethro Akroyd, Alexei A. Lapkin, Markus Kraft

Related Publications

Explore these studies to deepen your understanding of the subject.

Engineering and Technology

From the teapot effect to tap-triggered self-wetting: a 3D self-driving sieve for whole blood filtration

Y. Li, X. Li, et al.

Transportation

ARE WE READY TO EMBRACE CONNECTED AND SELF-DRIVING VEHICLES? A CASE STUDY OF TEXANS

P. Bansal and K. M. Kockelman

Education

Interpretable early warning recommendations in interactive learning environments: a deep-neural network approach based on learning behavior knowledge graph

X. Xia and W. Qi

Biology

Self-driving laboratories to autonomously navigate the protein fitness landscape

J. T. Rapp, B. J. Bremer, et al.

Listen, Learn & Level Up

Over 10,000 hours of research content in 25+ fields, available in 12+ languages.

No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.

listen to research audio papers with researchbunny