Human-Robot Co-Adaptation
How people and robots mutually adapt to one another over repeated interaction, as part of a proposed NSF center on human-robot co-adaptation.
As robots move out of controlled settings and into homes, workplaces, and public spaces, the central problem is no longer how a robot performs a fixed task but how a person and a robot adapt to each other over repeated interaction. This work brings the lab’s methods for measuring interpersonal coordination - multimodal behavioral capture, linguistic alignment, and dynamical systems analysis - to bear on human-robot interaction, treating co-adaptation as a coupled system rather than as a property of either partner alone.
This is a proposed NSF center effort with Joydeep Biswas, Roberto Martin-Martin, Justin Hart, and Chen Yu at UT Austin.
Selected papers
This project is new; the work below establishes the methods it draws on.
- Duran, N. D., Paxton, A., & Fusaroli, R. (2019). ALIGN: Analyzing linguistic interactions with generalizable techNiques—a Python library. Psychological Methods. [PDF]
- Duran, N. D., Paige, A., & D’Mello, S. K. (2024). Multi-level linguistic alignment in a dynamic collaborative problem-solving task. Cognitive Science, 48, e13398. [PDF]
See the full list on the publications page.