For You, Not for Everyone: Bystander-Aware Delivery of Critical Feedback in Robot Tutoring
For You, Not for Everyone: Bystander-Aware Delivery of Critical Feedback in Robot Tutoring
This arXiv preprint presents a study on robot tutoring where critical feedback is delivered to an individual learner while managing the presence of bystanders. The research compares two robot behaviors: context-invariant (delivering feedback aloud regardless of surroundings) and context-adaptive (detecting bystanders, turning away, and displaying feedback silently). In a between-subjects study with 40 participants, the context-adaptive behavior led to higher ratings in perceived privacy awareness and social competence compared to the invariant condition. The authors note that evidence for reduced experienced embarrassment was inconclusive. The findings inform the design of robots that adapt communication to sensitive information based on bystander presence.
The study compares context-invariant and context-adaptive robot behaviors in a between-subjects experiment with 40 participants, finding that adaptive behaviors (scanning for bystanders, turning away, silent display output) improved ratings of perceived privacy awareness and social competence compared to invariant behaviors, though evidence for reduced embarrassment was inconclusive.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- ScriptedOpen source S3
Reported numbers
critical feedback messages
2
View original evidence
40 participants. Following an initial phase without a bystander, a bystander entered the setting. Participants then received two scripted critical feedback messages concerning their pronunciation and handwriting, independent of their actual performance. With the context-invariant behavior, the robot tutor delivered both messages aloud. With the context-adaptive behavior, the robot tutor scanned for the bystander, tu
Open source S3
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
40 participants. Following an initial phase without a bystander, a bystander entered the setting. Participants then received two scripted critical feedback messages concerning their pronunciation and handwriting, independent of their actual performance. With the context-invariant behavior, the robot tutor delivered both messages aloud. With the context-adaptive behavior, the robot tutor scanned for the bystander, tu
Open source S3
rned its body and display away after detecting them, gave a spoken attention cue, and presented the same feedback messages silently on its display. Participants rated the robot tutor higher in perceived privacy awareness and perceived social competence in the context-adaptive condition than in the context-invariant condition, while evidence for reduced experienced embarrassment was inconclusive. These findings inform
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org