Seamless integration of legacy robotic systems into a self-driving laboratory via NIMO: a case study on liquid handler automation

<p>The orchestration software (OS) for controlling self-driving laboratories (SDLs) has been advanced significantly in recent years. We developed NIMO (formerly NIMS-OS, NIMS Orchestration System), an OS explicitly designed to integrate multiple artificial intelligence (AI) algorithms with div...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Ryo Tamura (1957942) (author)
مؤلفون آخرون: Hiromichi Taketa (22302314) (author), Satoshi Murata (423118) (author), Daisuke Ryuno (22302317) (author), Tomotaka Yokota (22302320) (author), Koji Tsuda (86274) (author), Shoichi Matsuda (448382) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852016319433539584
author Ryo Tamura (1957942)
author2 Hiromichi Taketa (22302314)
Satoshi Murata (423118)
Daisuke Ryuno (22302317)
Tomotaka Yokota (22302320)
Koji Tsuda (86274)
Shoichi Matsuda (448382)
author2_role author
author
author
author
author
author
author_facet Ryo Tamura (1957942)
Hiromichi Taketa (22302314)
Satoshi Murata (423118)
Daisuke Ryuno (22302317)
Tomotaka Yokota (22302320)
Koji Tsuda (86274)
Shoichi Matsuda (448382)
author_role author
dc.creator.none.fl_str_mv Ryo Tamura (1957942)
Hiromichi Taketa (22302314)
Satoshi Murata (423118)
Daisuke Ryuno (22302317)
Tomotaka Yokota (22302320)
Koji Tsuda (86274)
Shoichi Matsuda (448382)
dc.date.none.fl_str_mv 2025-09-24T08:40:06Z
dc.identifier.none.fl_str_mv 10.6084/m9.figshare.30196478.v1
dc.relation.none.fl_str_mv https://figshare.com/articles/dataset/Seamless_integration_of_legacy_robotic_systems_into_a_self-driving_laboratory_via_NIMO_a_case_study_on_liquid_handler_automation/30196478
dc.rights.none.fl_str_mv CC BY
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Medicine
Microbiology
Pharmacology
Ecology
Sociology
Computational Biology
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
Self-driving laboratory
liquid handler automation
Bayesian optimization
dc.title.none.fl_str_mv Seamless integration of legacy robotic systems into a self-driving laboratory via NIMO: a case study on liquid handler automation
dc.type.none.fl_str_mv Dataset
info:eu-repo/semantics/publishedVersion
dataset
description <p>The orchestration software (OS) for controlling self-driving laboratories (SDLs) has been advanced significantly in recent years. We developed NIMO (formerly NIMS-OS, NIMS Orchestration System), an OS explicitly designed to integrate multiple artificial intelligence (AI) algorithms with diverse exploratory objectives. NIMO provides a framework for integrating AI into robotic experimental systems that are controlled by other OS platforms based on both Python and non-Python languages. In this study, we demonstrate the realization of an SDL via NIMO by integrating AI into a legacy robotic system. As a proof of concept, we integrated an automated liquid handling system controlled by a Visual Basic (VB) program into the SDL through NIMO and performed parameter optimization of the dispensing process using Bayesian optimization, thereby enabling autonomous and automated experiments. NIMO facilitates AI integration through straightforward file exchanges, ensuring compatibility with robotic experimental systems programmed in non-Python languages such as VB and LabVIEW, as well as SDLs managed by other OS platforms. We anticipate that NIMO’s ability to support a broad spectrum of AI-driven autonomous experiments will significantly enhance the functionality and versatility of SDLs.</p> <p>NIMO enables AI-driven automation in self-driving labs by bridging diverse experimental systems, including those using non-Python platforms, greatly enhancing SDL accessibility and flexibility.</p>
eu_rights_str_mv openAccess
id Manara_586de697be98f07410ab55a3cc8a7668
identifier_str_mv 10.6084/m9.figshare.30196478.v1
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30196478
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY
spelling Seamless integration of legacy robotic systems into a self-driving laboratory via NIMO: a case study on liquid handler automationRyo Tamura (1957942)Hiromichi Taketa (22302314)Satoshi Murata (423118)Daisuke Ryuno (22302317)Tomotaka Yokota (22302320)Koji Tsuda (86274)Shoichi Matsuda (448382)MedicineMicrobiologyPharmacologyEcologySociologyComputational BiologySpace ScienceBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedSelf-driving laboratoryliquid handler automationBayesian optimization<p>The orchestration software (OS) for controlling self-driving laboratories (SDLs) has been advanced significantly in recent years. We developed NIMO (formerly NIMS-OS, NIMS Orchestration System), an OS explicitly designed to integrate multiple artificial intelligence (AI) algorithms with diverse exploratory objectives. NIMO provides a framework for integrating AI into robotic experimental systems that are controlled by other OS platforms based on both Python and non-Python languages. In this study, we demonstrate the realization of an SDL via NIMO by integrating AI into a legacy robotic system. As a proof of concept, we integrated an automated liquid handling system controlled by a Visual Basic (VB) program into the SDL through NIMO and performed parameter optimization of the dispensing process using Bayesian optimization, thereby enabling autonomous and automated experiments. NIMO facilitates AI integration through straightforward file exchanges, ensuring compatibility with robotic experimental systems programmed in non-Python languages such as VB and LabVIEW, as well as SDLs managed by other OS platforms. We anticipate that NIMO’s ability to support a broad spectrum of AI-driven autonomous experiments will significantly enhance the functionality and versatility of SDLs.</p> <p>NIMO enables AI-driven automation in self-driving labs by bridging diverse experimental systems, including those using non-Python platforms, greatly enhancing SDL accessibility and flexibility.</p>2025-09-24T08:40:06ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.6084/m9.figshare.30196478.v1https://figshare.com/articles/dataset/Seamless_integration_of_legacy_robotic_systems_into_a_self-driving_laboratory_via_NIMO_a_case_study_on_liquid_handler_automation/30196478CC BYinfo:eu-repo/semantics/openAccessoai:figshare.com:article/301964782025-09-24T08:40:06Z
spellingShingle Seamless integration of legacy robotic systems into a self-driving laboratory via NIMO: a case study on liquid handler automation
Ryo Tamura (1957942)
Medicine
Microbiology
Pharmacology
Ecology
Sociology
Computational Biology
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
Self-driving laboratory
liquid handler automation
Bayesian optimization
status_str publishedVersion
title Seamless integration of legacy robotic systems into a self-driving laboratory via NIMO: a case study on liquid handler automation
title_full Seamless integration of legacy robotic systems into a self-driving laboratory via NIMO: a case study on liquid handler automation
title_fullStr Seamless integration of legacy robotic systems into a self-driving laboratory via NIMO: a case study on liquid handler automation
title_full_unstemmed Seamless integration of legacy robotic systems into a self-driving laboratory via NIMO: a case study on liquid handler automation
title_short Seamless integration of legacy robotic systems into a self-driving laboratory via NIMO: a case study on liquid handler automation
title_sort Seamless integration of legacy robotic systems into a self-driving laboratory via NIMO: a case study on liquid handler automation
topic Medicine
Microbiology
Pharmacology
Ecology
Sociology
Computational Biology
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
Self-driving laboratory
liquid handler automation
Bayesian optimization