Beyond Activation: Gaze Invocation with Visible Status for an Embodied AR Assistant in Co-Located Collaboration
3.80T1 sourcearXiv cs.HC
Source record
Published by arXiv cs.HC (T1 source). The original is at https://arxiv.org/abs/2610.09284.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryResearch paper proposing gaze-based activation for an embodied AR assistant in co-located settings, with visible listening status on the assistant's body to manage activation, continued interaction, and release. A 25-participant study (500 interaction outcomes) found gaze acquisition preceded speech in 98.8% of attempts, but revealed a release problem: users missed status changes when gaze returned to work.
Why it mattersEmpirical study of a concrete interaction pattern for AR assistant address and turn management — relevant evidence for anyone designing or evaluating embodied AI assistants, with measured failure modes included.
Cited by
No citations on record.
