Papers
2
Total Citations
8
H-Index
2
About
Shu Pan’s research lies at the intersection of human-robot interaction, computational trust modeling, and cognitive robotics. Their major contributions center on understanding how human trust in robots evolves and transfers across different tasks and contexts. In their highly cited 2019 work, Pan developed novel Bayesian non-parametric and neural network models to capture trust dynamics in multi-task settings, using real-world human-subjects data from Fetch robot interactions and virtual reality simulations. This work, alongside their 2018 study on trust transfer across robot capabilities, provides foundational insights into how humans calibrate trust when robots perform diverse tasks—from household chores to simulated environments. Together, these papers have garnered significant attention (4 citations each), establishing Pan as a key voice in computational trust research. Their findings have implications for designing more adaptive and trustworthy autonomous systems, particularly in domains requiring flexible human-robot collaboration. Pan’s work is essential reading for researchers exploring the cognitive and computational underpinnings of human-robot trust.
Research Focus
Key Achievements
Top Papers
- 1
- 2The Transfer of Human Trust in Robot Capabilities across Tasks4 citations · 2018