Towards Genuine Robot Teammates: Improving Human-Robot Team Performance Beyond Shared Mental Models with Proactivity

2024

Collection: Emerging Frontiers in Human-Robot Interaction
Publisher: Springer Nature

Gwendolyn Edgar and Ayca Aygun and Matthew McWilliams and Matthias Scheutz

Recent work in human-robot teaming has demonstrated that when robots build and maintain "shared mental models", the effectiveness of the whole human-robot team is overall better compared to a baseline with no shared mental models. In this work, we expand on this insight by introducing proactive behaviors in addition to shared mental models to investigate potential further improvements of team performance and task efficiency. We developed a set of proactive robot behaviors that we experimentally compared to baseline "reactive" behaviors, hypothesizing that, combined with shared mental models, robots with these more proactive behaviors will become even more effective teammates. The results from a human subject evaluation showed that proactive robot behaviors improves task efficiency and performance over mere reactive behaviors and objectively lowered human workload as measured by percentage change in the subject's pupil size.

@incollection{edgaretal24,
  title={Towards Genuine Robot Teammates: Improving Human-Robot Team Performance Beyond Shared Mental Models with Proactivity},
  author={Gwendolyn Edgar and Ayca Aygun and Matthew McWilliams and Matthias Scheutz},
  year={2024},
  booktitle={Emerging Frontiers in Human-Robot Interaction},
  publisher={Springer Nature},
  url={https://hrilab.tufts.edu/publications/edgaretal24.pdf}
}