Session D30: Self-Driving Labs: Autonomous, High-throughput Experimentation and Modeling in Polymer Physics

Self-driving Lab (Polybot) for electronic polymer discovery

Autonomous platform is the integration of high-throughput robotic experimentation and characterization with data-driven model development to guide the search for targeted formulation and processing conditions. While autonomous/self-driving laboratories have made great advances in pharmaceuticals, hard materials, and organic small molecules, the development of such systems for polymeric materials is in a relatively nascent stage. This research aims to develop an autonomous discovery platform in Polybot self-driving lab that allows us to rapidly go from a polymer material concept to realized manifestations of final, testable materials targeted at relevant properties. In this talk, I will focus on the autonomous discovery of electrochromic properties of polymers that have full-color tunable optical properties and reversibly modulated optical transmission under applied potentials for energy-saving and color-tunable applications. I will also talk about closed-loop solution processing electronic polymers for desirable functions. Our approach involves automated condition optimization, data mining, and structure-property prediction model building. By integrating of Globus data management system, which can interact with all the required experimental equipment, our predictive ML model can guide the autonomous discovery, facilitating non-human intervention throughout the close-loop exploration process for a new polymer formulation with targeted electronic properties.      

Unravelling the Extreme Mechanics of Hierarchical Polymers using Self-Driving Labs

The development of advanced materials is extremely slow considering the pressing needs presented by societal challenges. A major reason for this pace is the vastness of possible compositions/processing conditions that must be navigated as part of the discovery/design/development process, which motivates the development of new approaches to accelerate the materials development pipeline. Our work focuses on the use of self-driving labs (SDL), or the combination of automation to perform experiments without human intervention and machine learning to select experiments that best progress toward a user-defined goal. In this talk, we overview our progress applying self-driving labs towards the development of materials that absorb mechanical energy. In particular, materials and architectures that are tough are ubiquitous as protective equipment and structural elements. If such materials could be engineered to absorb more energy per unit weight or volume while remaining easy to produce out of sustainable materials, they could find fruitful application in a number of fields. To explore this, we develop a SDL that combines additive manufacturing and mechanical testing and explore the toughness of 3D printed components. First, we use this platform to benchmark the acceleration provided through the use of SDL and find that this process allows us to identify high performing structures ~60 times faster than grid-based searching, which comprised the first experimental benchmarking of SDLs. Subsequently, we incorporated finite element analysis (FEA) into this SDL to search in a physics-aware fashion and observe further acceleration. Finally, we describe an extensive experimental campaign in which we find structures composed of biodegradable polymers that obtain superlative energy absorbing efficiency.   

Automation and Active Learning for the Autonomous Design of Polymer Biomaterials

The seamless integration of synthetic materials with biological systems long remains a grand challenge, often curtailed by the sheer complexity of the cell-material interface. For decades, biomaterial scientists and engineers have designed around this complexity by rationally designing new materials one experiment at a time. However, recent advances in laboratory automation, high throughput analytics, and artificial intelligence / machine learning (AI/ML) now provide a unique opportunity to fully automate the design process. In this seminar, we put forth our efforts to develop a biomaterials acceleration platform (BioMAP) (i.e., self-driving biomaterials lab) that can rapidly iterate through design spaces and identify unique material properties that perfectly synergize with biological complexity.   

The NIST Autonomous Formulation Laboratory: Solving Industrial Problems with X-Ray and Neutron Scattering and AI

Liquid formulations are ubiquitous, ranging from products such as deicing liquids to food/beverages and biologic drugs. All such products involve precisely tuned composition to enable engineered behaviors, whether that be a drug targeting high-pH tumor areas or a deicing fluid thinning at a specific shear rate so a plane takes off. These engineered responses often involve dozens of interconnected active components ranging from viscosity modifiers to dyes, preservatives, fragrances, etc. This complexity often precludes rational, physics-based optimization of product design in response to changing regulatory/sustainability drivers, for example. This talk will describe the Autonomous Formulation Laboratory, a project based at NIST that is capable of autonomously mixing liquids in arbitrary, n-dimensional composition space and characterizing the resulting formulation using x-ray and neutron scattering in combination with spectroscopy, rheology, and other measurments. This platform is driven by custom, highly flexible open source software that can be used to tackle a variety of different problems, from mapping the bounds of a specific, target phase with high accuracy to maximizing overall phase diagram exploration and everything in between. This talk will describe our development and application of the system to a variety of industrial formulation problems and recent efforts to provide highly robust, flexible data classifiers and data fusion approaches to make the most of multimodal data.   

Tsuchinoko: a GUI for Autonomous Experiments

Tsuchinoko is a GUI application for visualization and control of intelligent, autonomous experiments. This project aims to deliver the power of adaptive experimental engines (i.e. gpCAM) to general synchrotron users with visualizations that facilitate exploration and exposition of autonomous experimental data/procedures. It is agnostic of experimental design, autonomous engine, and measurement systems. The design of Tsuchinoko follows modular service-oriented architecture such that computationally heavy or experimental control components may be dislocated from the client application for remote computing/execution.

This talk will present Tsuchinoko in the context of soft matter and polymer science problems, including demonstration and discussion of experiments run at NSLS-II at the CMS beamline.

Tsuchinoko is a Python Qt application which leverages OpenGL accelerated visualizations and the PyQtGraph library.