autoHSP: An Autonomous Experimentation Framework for Determining Hansen Solubility Parameters via Active Learning
Start Date:
- Built a closed-loop, autonomous experimentation framework that integrates ML-driven decision-making with automation.
- Implemented a batch-mode active learning algorithm for experiment design and a computer vision pipeline for data analysis.
- Proposed a scalable and accessible blueprint for autonomous research and self-driving laboratories.
I gave a talk on this project at the 2024 Chemistry Graduate Summer Seminar at Carnegie Mellon University.