Vivienne Bihe
Papers
9
Total Citations
66
H-Index
6
About
Vivienne Bihe is a leading researcher at the intersection of human-robot interaction, machine learning, and moral psychology, whose work fundamentally rethinks how robots learn social norms from people. Her core research investigates the dynamic processes of trust updating during interactive teaching, demonstrating in a well-powered study (n=220) that humans continuously recalibrate their trust across repeated robot interactions. Bihe has pioneered the study of how people naturally combine instructive and evaluative feedback when teaching norms to robots, developing reward models that accommodate diverse human teaching styles. Her highly cited 2023 paper on dynamic trust updating (17 citations) and her 2022 work on norm learning from mixed feedback (9 citations) have established foundational frameworks for the field. Notably, she has developed systematic methods for studying moral human-robot interaction, including how robots should handle norm conflicts and how prosocial observations can cultivate new norms toward delivery robots. Her research shows that interactive teaching can recover and build trust even with imperfect learners, a critical insight for deploying robots in social communities. Bihe’s work is essential reading for anyone interested in creating robots that can learn, earn trust, and act appropriately in human social spaces.
Research Focus
Key Achievements
Top Papers
- 1People Dynamically Update Trust When Interactively Teaching Robots17 citations · 2023
- 2
- 3
- 4Instruct or Evaluate: How People Choose to Teach Norms to Social Robots8 citations · 2022
- 5
- 6
- 7
- 8What Properties of Norms can we Implement in Robots?*4 citations · 2023
- 9