English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Chemistry experimentation is often resource- and labor-intensive. Despite themany benefits incurred by the integration of advanced and special-purpose labequipment, many aspects of experimentation are still manually conducted bychemists, for example, polishing an electrode in electrochemistry experiments.Traditional lab automation infrastructure faces challenges when it comes toflexibly adapting to new chemistry experiments. To address this issue, wepropose a human-friendly and flexible robotic system, ORGANA, that automates adiverse set of chemistry experiments. It is capable of interacting withchemists in the lab through natural language, using Large Language Models(LLMs). ORGANA keeps scientists informed by providing timely reports thatincorporate statistical analyses. Additionally, it actively engages with userswhen necessary for disambiguation or troubleshooting. ORGANA can reason overuser input to derive experiment goals, and plan long sequences of bothhigh-level tasks and low-level robot actions while using feedback from thevisual perception of the environment. It also supports scheduling and parallelexecution for experiments that require resource allocation and coordinationbetween multiple robots and experiment stations. We show that ORGANAsuccessfully conducts a diverse set of chemistry experiments, includingsolubility assessment, pH measurement, recrystallization, and electrochemistryexperiments. For the latter, we show that ORGANA robustly executes along-horizon plan, comprising 19 steps executed in parallel, to characterizethe electrochemical properties of quinone derivatives, a class of moleculesused in rechargeable flow batteries. Our user study indicates that ORGANAsignificantly improves many aspects of user experience while reducing theirphysical workload. More details about ORGANA can be found athttps://ac-rad.github.io/organa/.

ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization