Pharma LPII - Digital Apprentice: Learning and Teaching Expert Instrument Skill
Some laboratory instruments take months to learn. An experienced operator can tell within seconds that a measurement is going wrong; a new user usually cannot, and the mistake is expensive. Almost none of that expertise is written down anywhere: it passes from one person to the next by watching over a shoulder, and it does not scale.
Faculty Advisor:
Description:
Some laboratory instruments take months to learn. An experienced operator can tell within seconds that a measurement is going wrong; a new user usually cannot, and the mistake is expensive. Almost none of that expertise is written down anywhere: it passes from one person to the next by watching over a shoulder, and it does not scale.
This team studies that problem using atomic force microscopy, an instrument widely used to characterize pharmaceutical formulations and drug-carrier materials and one that is genuinely hard to learn. We record how experienced and inexperienced operators actually work, turn what we observe into structured training material, build a software environment where a new user can practice the hardest steps without damaging hardware and then test whether that practice transfers to the real instrument.
You will spend time on a research-grade AFM within your first few weeks. Students with no prior lab or programming background have real work from day one, running measurement sessions, reviewing and annotating recordings, writing and testing procedure documentation and running practice trials with new users. Students who arrive with more preparation take on the practice environment itself, the analysis of performance data or an extended-reality guidance interface at the instrument.
By the end of Spring 2027, the team will have one instrument procedure fully documented, a working practice environment and measured results on whether it helps, presented at the Office of Undergraduate Research expo, with a manuscript as the goal.
Prerequisites:
Required:
- None. Open to all majors and all years, including first-year students, with no prior lab or programming experience assumed. Every student has a defined role from week one.
Good to have (any one, not all):
- Python
- Video or data annotation
- Interest in human factors, training or how people learn
- Unity, Blender or game development
- CAD
- Electronics or embedded systems
- Prior lab coursework
- Machine learning
- Statistics
Preferred Majors:
Industrial Engineering, Mechanical Engineering, Electrical and Computer Engineering, Materials Engineering, Computer Science, Industrial and Physical Pharmacy, Pharmaceutical Sciences, Data Science and Psychology or Human Factors.
Students from other majors are genuinely welcome.