Alexandria Pabst
Papers
2
Total Citations
11
H-Index
2
About
Alexandria Pabst is a pioneering researcher in Human-Robot Interaction (HRI), specializing in how robots can detect and recover from task failures by interpreting subtle human social cues. Her work addresses a critical challenge in robotics: enabling autonomous systems to recognize their own errors in real-world, complex environments. Pabst’s key contributions include developing frameworks that leverage bystander reactions—such as confusion, smirks, or giggles—as implicit feedback for error detection, moving beyond explicit commands. Her 2023 overview paper, “Using Social Cues to Recognize Task Failures for HRI,” has garnered 6 citations, establishing foundational knowledge in this emerging area. She also created the Bystander Affect Detection (BAD) Dataset, a novel resource with 5 citations that provides annotated examples of human responses to robot mistakes, enabling machines to learn from social context. This dataset is a vital tool for advancing robot social intelligence and resilience. Pabst’s work bridges affective computing and robotics, promising more intuitive, adaptive machines. Her research is essential reading for students and engineers aiming to build robots that gracefully handle errors in human-centered settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2