Erin Hedlund
Papers
2
Total Citations
24
H-Index
2
About
Erin Hedlund is a leading researcher in human-robot interaction, with a primary focus on Learning from Demonstration (LfD) algorithms that enable non-expert users to teach robots new skills. Her work addresses a critical gap in robotics: understanding how a robot’s own performance influences the human teacher during the learning process. In her highly cited 2021 paper, “The Effects of a Robot's Performance on Human Teachers for Learning from Demonstration Tasks” (20 citations), Hedlund demonstrated that robot failure significantly alters human teaching behavior and trust—a finding with profound implications for designing adaptive, user-friendly robotic systems. She further advanced the field by developing personalized embeddings to improve robot-centric LfD approaches like Dataset Aggregation (DAgger), which traditionally struggle with human teachers. Her research bridges machine learning and cognitive science, showing that effective robot learning requires not just algorithmic improvements but also a deep understanding of human psychology. Hedlund’s contributions are shaping the next generation of collaborative robots that can learn naturally from everyday users, making her work essential reading for anyone interested in the future of human-robot collaboration.
Research Focus
Key Achievements
Top Papers
- 1
- 2