ChemOS: An Orchestration Software to Democratize Autonomous Discovery

Abstract

Autonomous or "self-driving" laboratories combine robotic platforms with artificial intelligence to increase the rate of scientific discovery. They have the potential to transform our traditional approaches to experimentation. Although autonomous laboratories recently gained increased attention, the requirements imposed by engineering the software packages often prevent their development. Indeed, autonomous laboratories require considerable effort in designing and writing advanced and robust software packages to control, orchestrate and synchronize automated instrumentations, cope with databases, and interact with various artificial intelligence algorithms. To overcome this limitation, we introduce ChemOS, a portable, modular and versatile software package, which supplies the structured layers indispensable for operating autonomous laboratories. Additionally, it enables remote control of laboratories, provides access to distributed computing resources, and comprises state-of-theart machine learning methods. We believe that ChemOS will reduce the time-to-deployment from automated to autonomous discovery, and will provide the scientific community with an easy-to-use package to facilitate novel discovery, at a faster pace.

Progress and prospects for accelerating materials science with automated and autonomous workflows

“…44 Algorithms such as Phoenics 63 have been specically developed for chemistry experiments and integrated into workow management soware such as ChemOS. 64 The carbon nanotube (CNT) autonomous research system (ARES) project, 65 which is discussed further below, is an example of a closed-loop system of a workow where tasks such as data interpretation are readily automated. There have been additional implementations of active learning in materials science to accelerate individual tasks, for example by acquiring only the necessary X-ray diffraction patterns for phase diagram characterization.…”

Toward “On‐Demand” Materials Synthesis and Scientific Discovery through Intelligent Robots

“…The future materials discovery needs not only the robot‐assisted workforce but upgrade of methodology to make synthesis really “predictable.” The “Dial a Molecule” program in the UK and the DARPA project “Make it” in the USA are typical ongoing cases for “On‐Demand” molecule discovery . The discovery process should start from materials design, synthesis planning, automatic experiments, and characterization, to parameter self‐adjusting autonomously to achieve a closing‐loop process . It needs an intelligent brain that well coupled neuron networks, physical‐chemistry theory and scientists‐machine interactions .…”

Autochemistry: A Research Paradigm Based on Artificial Intelligence and Big Data

“…Current research architecture cannot handle the impact of modern artificial intelligence 2 , or it merely focuses on technical solutions based on classical information technology 3 . Moreover, most current solutions in chemistry and pharmaceutical research are based on at least the second-generation of artificial intelligence 4 or -if artificial neural networks (ANN) are used -do not cover the whole research process 5 .…”