Papers
7
Total Citations
145
H-Index
6
About
Fei Sha is a leading researcher at the intersection of artificial intelligence, robotics, and personalized education, with a particular focus on human-robot interaction and machine learning. Her work is distinguished by pioneering contributions to socially assistive robotics, where she has developed computational frameworks for personalized learning in early childhood education. Notably, her 2015 paper on designing a socially assistive robot for teaching number concepts to preschoolers (43 citations) exemplifies her approach to creating adaptive educational technologies. Sha has also made significant advances in machine perception, introducing a Bayesian Theory of Mind framework for nonverbal communication in human-robot interactions (38 citations), and developing active multi-view object recognition systems that enable robots to interactively explore and identify objects. Her research on metric learning for reinforcement learning agents (19 citations) addresses fundamental challenges in how AI systems represent and learn from their environments. Through her interdisciplinary work spanning cognitive science, robotics, and machine learning, Sha has established herself as a key figure in creating intelligent systems that can understand, interact with, and adapt to human users in meaningful ways.
Research Focus
Key Achievements
Top Papers
- 1
- 2A Bayesian Theory of Mind Approach to Nonverbal Communication38 citations · 2019
- 3
- 4Metric learning for reinforcement learning agents19 citations · 2011
- 5Active Multi-view Object Recognition and Online Feature Selection9 citations · 2017
- 6Towards Interactive Object Recognition6 citations · 2014
- 7