In shared settings, social robots may need to exchange information with an individual while limiting co-present others' access to or interpretation of that information. Publicly observable speech and gestures may not adequately support such exchanges. We investigate a wearable-mediated channel for discreet interaction that combines in-ear audio messages with deliberate rightward head tilts as responses. To examine its feasibility and participants' experiences, we studied 20 pairs (40 participants) playing a card game with a screen-based conversational agent representing a social robot, controlled by a researcher in a Wizard-of-Oz setup. Each pair played with and without the channel. One participant wore the device (the wearer), while the other (the non-wearer) was informed about the channel after gameplay. The channel conveyed information that could help the wearer or robot character select an opponent they could defeat. The information exchange and subsequent opponent selection occurred as intended in 39 of 40 channel-mediated turns. Wearers reported low perceived pressure/tension in both conditions, with no statistically significant difference between conditions, and favorable usability immediately after use. Retrospective interviews, however, revealed varied accounts of noticing the interaction among non-wearers and contrasting perceptions of teamwork and unfairness. These findings support the feasibility of wearable-mediated exchanges within this game and identify awareness and fairness as considerations for future designs.
Figures & tables
Figure 1. Two hypothetical scenarios illustrating discreet interaction. On the left, a social robot suggests ordering pizza to a mother via in-ear audio instead of raising the idea openly in front of the child. On the right, the robot uses the wearable-mediated channel to request permission before making a potentially embarrassing suggestion to an older adult. Both scenes illustrate a bidirectional exchange embedded within an ongoing shared activity. Generated with ChatGPT 6. Two illustrated hypothetical domestic applications of discreet interaction with social robots. On the left, a robot sends a suggestion to a mother while she cooks with a child. On the right, a robot offers assistance during a conversation between an older adult and a younger visitor. In both scenes, in-ear audio and a deliberate rightward head-tilt response illustrate a bidirectional exchange embedded within an ongoing shared activity.
Figure 2. Study setup for the three-player card game: (a) schematic showing the wearer and non-wearer seated across a table, with the screen-based robot character acting as both host and fellow player. In the discreet condition, the wearer used an in-ear wearable to receive in-ear audio and perform a deliberate rightward head-tilt response. The non-wearer remained an active participant and was not informed about the wearable-mediated channel until after gameplay; (b) the robot character displayed on the screen; (c) the cardholder camera feed showing the robot character’s card; and (d) the overhead camera feed showing the table and the participants’ revealed cards. Both camera feeds were available to the researcher controlling the robot character. Four panels illustrate the study setup. The top schematic shows two participants seated across a table with a screen-based robot character between them. The wearer uses an in-ear device, while the non-wearer is not informed of the channel. The bottom panels show the robot character on the screen, a rock card in the cardholder camera feed, and an overhead camera view of the table and participants holding cards.
Figure 3. Information flow in the Wizard-of-Oz setup. The researcher monitored the cardholder and overhead camera feeds and controlled the screen-based robot character’s speech, expressions, and movements through the robot GUI. In the discreet condition, the researcher used the earable GUI to deliver a card-information cue when the wearer was the guesser or a binary-response prompt when the robot character was the guesser. Following the binary-response prompt, detection of a qualifying rightward head tilt set the displayed response state to “yes,” while non-detection within three seconds set it to “no.” The researcher monitored this state to guide the robot character’s opponent selection. In the baseline condition, the robot GUI selected the robot character’s opponent using its random-selection function. Interaction-flow diagram arranged from observation and researcher control to the robot character and participants. Solid arrows show the flow used in the baseline and discreet conditions: the researcher observes the cardholder camera feed and the overhead camera feed, operates the robot GUI, and triggers the robot character's publicly observable behavior. Dashed arrows show the additional discreet condition flow: the researcher selects a card-information cue or binary-response prompt in the earable GUI; the wearer receives in-ear audio and can perform the deliberate rightward head-tilt response; the eSense IMU supports detection or non-detection of a qualifying rightward head tilt, and the displayed response state informs the researcher.
Figure 4. Wearer-reported perceived pressure/tension and usability outcomes. Two panels showing wearer-reported outcomes. Left: boxplots of perceived pressure/tension scores in the baseline and discreet conditions. Right: boxplots of USE dimension scores for usefulness, ease of use, ease of learning, and satisfaction after the discreet condition, with the scale midpoint marked.