Human Perceptions of a Curious Robot that Performs Off-Task Actions

Abstract

Researchers have proposed models of curiosity as a means to drive robots to learn and adapt to their environments. While these models balance goal- and exploration-oriented actions in a mathematically principled manor, it is not understood how users perceive a robot that pursues off-task actions. Motivated by a model of curiosity based on intrinsic rewards, we conducted three online video-surveys with a total of 264 participants, evaluating a variety of curious behaviors. Our results indicate that a robot’s off-task actions are perceived as expressions of curiosity, but that these actions lead to a negative impact on perceptions of the robot’s competence. When the robot explains or acknowledges its deviation from the primary task, this can partially mitigate the negative effects of off-task actions.

BibTeX Entry

@inproceedings{walker2020perceptions,
  author = {Walker, Nick and Weatherwax, Kevin and Alchin, Julian and Takayama, Leila and Cakmak, Maya},
  title = {Human Perceptions of a Curious Robot that Performs Off-Task Actions},
  booktitle = {Proceedings of the 2020 ACM/IEEE International Conference on Human-Robot Interaction (HRI)},
  location = {Oxford, UK},
  month = mar,
  year = {2020},
  doi = {10.1145/3319502.3374821},
  wwwtype = {conference},
  wwwpdf = {https://hcrlab.cs.washington.edu/assets/pdfs/2020/walker2020perceptions.pdf},
  wwwvideo = {https://www.youtube.com/watch?v=1j91ISstdH8},
  wwwextra = {https://doi.org/10.5281/zenodo.3600599}
}