Papers
2
Total Citations
167
H-Index
2
About
Carolyn Chen is a pioneer at the intersection of surgical education and human-robot interaction. Her research focuses on developing novel methods to evaluate and improve technical performance, with a particular emphasis on surgical skills assessment and bilateral robotic manipulation. Chen’s most influential work introduced the Crowd-Sourced Assessment of Technical Skills (CSATS), a groundbreaking approach that leverages non-expeer crowds to evaluate surgical performance. This 2013 paper, with 164 citations, demonstrated that crowd workers can provide reliable assessments comparable to expert surgeons, revolutionizing how surgical training is evaluated and scaled. In her more recent work, Chen tackles the challenge of teaching robots complex bilateral manipulation tasks. Her 2017 paper proposes an innovative algorithm using iterated best response demonstrations, addressing the difficulty human supervisors face when providing demonstrations for multi-arm coordination. While still early-stage with 3 citations, this work opens new possibilities for robot learning in manufacturing and surgery. Chen’s contributions bridge the gap between human expertise and machine learning, offering practical solutions for both surgical education and robotic skill acquisition.
Research Focus
Key Achievements
Top Papers
- 1
- 2