The AFL is a multi-facility collaborative project that originated at the National Institute of Standards and Technology (NIST), US Department of Commerce, and has since expanded to include partnerships with companies, academic laboratories, and facilities worldwide.
The AFL aims to provide open-source hardware, control software, and AI algorithms to accelerate materials optimization and discovery.
Credit: NIST / Dean M DeLongchamp
Our Mission
We are committed to advancing materials science by integrating automation, artificial intelligence, and advanced characterization techniques. Our objective is to expedite the discovery and optimization of complex liquid formulations, which are vital in various industries, including pharmaceuticals, personal care products, and coatings.
What We Offer
Open-Source Hardware
We provide designs and specifications for automated liquid handling systems capable of precise and reproducible formulation synthesis.
Tutorials
Learn how to use the AFL platform through our comprehensive tutorials and guides.
Control Software
Our automation software facilitates seamless integration and operation of laboratory equipment, enabling both manual and autonomous experiments.
AI Algorithms
We develop and share artificial intelligence algorithms that drive autonomous experimentation, enabling rapid exploration of formulation spaces and optimization of material properties.
Program Overview
The Autonomous Formulation Laboratory is a joint program between the nSoft consortium, NCNR, and NIST's Materials Measurement Lab focused on accelerating materials discovery and formulation optimization through artificial intelligence (AI) and machine learning (ML) directed, multimodal scattering experiments.
The core of the AFL platform is an open source, NCNR-developed platform to prepare liquid mixtures via pipetting, transfer those mixtures to a measurement cell, perform a SANS (or SAXS or other method) experiment, and provide the data to an AI guidance server.
Formulation engineering is at the core of soft materials-based products that cut across industry and everyday life: paints, vaccines, fuels, and shampoos are just a few examples of products that are formulated with tens to hundreds of individual components.
How to Get Involved
We welcome contributions from the community to enhance and expand the AFL's capabilities. Here's how you can participate:
- Collaborate: Join our network of researchers and institutions to work on joint projects or share data and insights.
- Contribute: Develop and submit improvements to our hardware designs, software codebase, or AI algorithms.
- Utilize: Leverage our resources in your own research or industrial applications, and provide feedback to help us improve.
If you are interested in replicating the AFL, or using it at the NCNR, please reach out to Dr. Peter Beaucage or Dr. Tyler Martin for more details!
Other facilities in the US and around the world will soon offer the AFL platform as a user facility and will be listed here.
Resources
- Documentation: Comprehensive guides and manuals are available in our GitHub repositories.
- Publications: Explore our research publications, including our 2023 Chemistry of Materials publication.
- Community Forum: Engage with other users, ask questions, and share experiences through our online community platform.
Our Repositories
- AFL-agent - Intelligent agent for formulation research
- AFL-automation - Automation systems for lab operations
- AFL-hardware - Hardware designs and specifications
- AFL-tutorial - Tutorials and learning resources
- AFL-andon - Cross-Machine Microservice Starting/Monitoring Platform
- AFL-watchdog - System stability and reliability tools