The Lab of the Future

The automation of experimental research activities plays a big role in accelerating scientific discovery - from ubiquitous software tools to “self-driving laboratories”. In order to achieve fully automated systems capable of conducting human-level scientific research, a plethora of challenges has to be overcome: while ensuring general interoperability and adaptability, providing orchestration of experiments and access to deep chemical knowledge, advanced capacities for reasoning and goal derivation need to be developed. We argue, that the current platform-centric approach is insufficient in this regard and might even limit further development. Our group therefore started developing solutions that are integrated within The World Avatar, an all-encompassing digital twin based on a dynamic knowledge graph.


The Digital Lab Framework

A change of perspective is needed to move the field from optimising few parameters within narrowly defined experimental setups to holistic lab automation that integrates all aspects of scientific laboratories and promises truly autonomous systems.

We therefore take on a systems engineering view that includes related knowledge about chemistry and error propagation as well as maintenance schedules, infrastructure, and utilities. We introduce the Digital Lab Framework as part of The World Avatar that aims to unify the capabilities of self-driving labs with electronic lab notebooks and inventory management systems as well as integrate information currently siloed in BIM, GIS, and BMS systems.

Above illustration is an overview of the intertwined aspects of a chemical research laboratory that are represented within our framework. Click on any of the intersection areas of the venn diagram to explore our work on those areas.


Previous Work

Our group has been working in this field since 2004, digitising and automating experimental research initially for educational purposes. Previous work has been conducted within the Weblabs project, offering remote control of real-life experiments as teaching methods.


Recent Associated Preprints

318: The Digital Lab Manager: Automating Research Support

Simon D. Rihm, Yong Ren Tan, Wilson Ang, Markus Hofmeister, Xinhong Deng, Michael Teguh Laksana, Hou Yee Quek, Jiaru Bai, Laura Pascazio, Sim Chun Siong, Jethro Akroyd, Sebastian Mosbach, and Markus Kraft, Technical Report 318, c4e-Preprint Series, Cambridge, 2024.

316: The Digital Lab Facility Manager: Using dynamic knowledge graph technology to automate operations of research laboratories

Simon D. Rihm, Yong Ren Tan, Wilson Ang, Hou Yee Quek, Xinhong Deng, Michael Teguh Laksana, Jethro Akroyd, Sebastian Mosbach, and Markus Kraft, Technical Report 316, c4e-Preprint Series, Cambridge, 2023.

314: The Digital Lab Framework as part of The World Avatar

Simon D. Rihm, Jiaru Bai, Aleksandar Kondinski, Sebastian Mosbach, Jethro Akroyd, and Markus Kraft, Technical Report 314, c4e-Preprint Series, Cambridge, 2023.

310: From Platform to Knowledge Graph: Distributed Self-Driving Laboratories

Jiaru Bai, Sebastian Mosbach, Connor J. Taylor, Dogancan Karan, Kok Foong Lee, Simon D. Rihm, Jethro Akroyd, Alexei A. Lapkin, and Markus Kraft, Technical Report 310, c4e-Preprint Series, Cambridge, 2023.

Funding

Funding has generously been provided by Cambridge-MIT Institute, Siemens SCE, and Pharma Innovation Programme Singapore (PIPS). This research was partly funded by the National Research Foundation (NRF), Prime Minister's Office, Singapore under its Campus for Research Excellence and Technological Enterprise (CREATE) programme.