OUR LAB FOCUSES ON...
Accelerating Materials Discovery and Innovation via
Predictive/Generative AI and Autonomous Robotic Platforms
01
Machine Intelligence Accelerated Discovery of Sustainable, Biobased Nanocomposites with Programmable Properties
Our research integrates machine learning (ML)-enabled predictive and generative modeling with collaborative robotics to accelerate the discovery of sustainable, biobased nanocomposites with programmable properties. We aim to develop all-natural plastic alternatives and antimicrobial, biobased food packaging films to address environmental plastic pollution challenges, food safety, quality preservation, and post-harvest contamination.
02
Designing Robust Machine Learning Frameworks for Limited Data Environments
Our research focuses on developing robust machine learning frameworks for limited-data applications in materials science and chemical engineering. Given the high cost and scarcity of experimental data, we aim to build predictive models that extract maximum insight from small datasets. By incorporating strategies such as active learning, transfer learning, data augmentation, and ensemble modeling, we enhance model accuracy and reliability, even in data-sparse settings. This approach has the potential to significantly accelerate materials discovery and process optimization, while reducing the time and cost of traditional experimentation.
03
Mechanically Driven Patterning of Functional Materials for Stretchable Electronics and Soft Robotics
Our research focuses on developing a versatile patterning strategy for engineering both homogeneous and heterogeneous topographies in functional materials and their nanocomposites. By harnessing multi-stage mechanical instabilities, we generate a library of hierarchical, multiscale topographies across a range of material systems. These tailored topographies are designed to enable advanced applications in stretchable electronics, soft robotics, and other emerging technologies that require mechanical adaptability and seamless functional integration.
04
Nanoconfined Synthesis of Catalytic Metal Nanocrystals
Our research explores how nano-confinement and key synthetic parameters influence the size, shape, and spatial distribution of catalytic metal nanocrystals. By uncovering detailed synthesis–structure–property relationships, we aim to construct a library of metal–2D material heterostructured catalysts with enhanced activity and selectivity for targeted reactions.
Contact Us
Affiliations
Department of Chemical and Biomolecular Engineering,
University of Maryland, College Park (UMD)
Maryland Robotics Center (MRC)
Contact
Email: checp@umd.edu
Phone: +1-(669)302-5418
Addresses
Campus Office: Room 1223C, 4418 Stadium Drive,
College Park, MD 20742-2111
Research Lab: Room 1216, J. M. Patterson Building,
College Park, MD 20742-2111
Zoom Office: Link