Large language models for chemistry robotics

This paper proposes an approach to automate chemistry experiments using robots by translating natural language instructions into robot-executable plans, using large language models together with task and motion planning. Adding natural language interfaces to autonomous chemistry experiment systems l...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Autonomous robots Ročník 47; číslo 8; s. 1057 - 1086
Hlavní autoři: Yoshikawa, Naruki, Skreta, Marta, Darvish, Kourosh, Arellano-Rubach, Sebastian, Ji, Zhi, Bjørn Kristensen, Lasse, Li, Andrew Zou, Zhao, Yuchi, Xu, Haoping, Kuramshin, Artur, Aspuru-Guzik, Alán, Shkurti, Florian, Garg, Animesh
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.12.2023
Springer Nature B.V
Témata:
Artificial Intelligence
Chemical synthesis
Chemistry
Computer Imaging
Constraints
Control
Domain specific languages
Engineering
Experiments
Iterative methods
Language
Large language models
Mechatronics
Motion planning
Natural language
Natural language processing
Pattern Recognition and Graphics
Planning
Program verification (computers)
Recrystallization
Robotics
Robotics and Automation
Robots
Skills
Translating
Vision
Plan generation verification
Constrained task and motion planning
Chemistry lab automation
Large language models
Self-driving labs
ISSN:0929-5593, 1573-7527
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper proposes an approach to automate chemistry experiments using robots by translating natural language instructions into robot-executable plans, using large language models together with task and motion planning. Adding natural language interfaces to autonomous chemistry experiment systems lowers the barrier to using complicated robotics systems and increases utility for non-expert users, but translating natural language experiment descriptions from users into low-level robotics languages is nontrivial. Furthermore, while recent advances have used large language models to generate task plans, reliably executing those plans in the real world by an embodied agent remains challenging. To enable autonomous chemistry experiments and alleviate the workload of chemists, robots must interpret natural language commands, perceive the workspace, autonomously plan multi-step actions and motions, consider safety precautions, and interact with various laboratory equipment. Our approach, CLAIRify , combines automatic iterative prompting with program verification to ensure syntactically valid programs in a data-scarce domain-specific language that incorporates environmental constraints. The generated plan is executed through solving a constrained task and motion planning problem using PDDLStream solvers to prevent spillages of liquids as well as collisions in chemistry labs. We demonstrate the effectiveness of our approach in planning chemistry experiments, with plans successfully executed on a real robot using a repertoire of robot skills and lab tools. Specifically, we showcase the utility of our framework in pouring skills for various materials and two fundamental chemical experiments for materials synthesis: solubility and recrystallization. Further details about CLAIRify can be found at https://ac-rad.github.io/clairify/ .
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0929-5593
1573-7527
DOI:10.1007/s10514-023-10136-2