@inproceedings{manaseryan-etal-2026-looking,
title = "Looking for Objects and Looking for Help: Robot Gaze Elicits Human Cooperation",
author = "Manaseryan, Anna and
Bui, Thi Lan Anh and
Kennington, Casey",
editor = "Ghaleb, Esam and
Takmaz, Ece and
Frassinelli, Diego and
Khaertdinov, Bulat and
Fern{\'a}ndez, Raquel and
Yumak, Zerrin and
Ozyurek, Asli",
booktitle = "Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mint-1.12/",
pages = "105--116",
ISBN = "979-8-89176-482-8",
abstract = "Robots that search for objects on their own must decide what to do when the search fails, and how they signal that failure to a human partner can determine whether the interaction turns into collaboration. Prior work on human{--}robot interaction has studied nonverbal help-seeking and social gaze separately, but rarely compares gaze against a matched verbal failure signal inside a live, real-time embodied search task. We present an embodied dialogue system, built on the Retico incremental processing framework, where the Cozmo robot searches for a specified object and signals failure either verbally or through gaze towards the human partner. We first compare a rule-based planner against a vision-language model (VLM) planner that reasons over scene semantics, finding that the VLM planner succeeds far more often (87.2{\%} vs. 65.9{\%}). We then test whether gaze can close this gap without adding reasoning capability to the rule-based planner. Adding gaze as the stuck signal raises success to 87.87{\%}, matching the VLM planner, while a verbal stuck signal only raises it slightly (68.75{\%}). Results further show that this effect is largely implicit: participants helped more in the gaze condition without consistently reporting that they felt invited to do so. Our findings suggest that gaze can substitute for reasoning capability a robot lacks, helping it elicit assistance from a human partner."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="manaseryan-etal-2026-looking">
<titleInfo>
<title>Looking for Objects and Looking for Help: Robot Gaze Elicits Human Cooperation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Manaseryan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thi</namePart>
<namePart type="given">Lan</namePart>
<namePart type="given">Anh</namePart>
<namePart type="family">Bui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Casey</namePart>
<namePart type="family">Kennington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Esam</namePart>
<namePart type="family">Ghaleb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ece</namePart>
<namePart type="family">Takmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Frassinelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bulat</namePart>
<namePart type="family">Khaertdinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Fernández</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zerrin</namePart>
<namePart type="family">Yumak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Ozyurek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-482-8</identifier>
</relatedItem>
<abstract>Robots that search for objects on their own must decide what to do when the search fails, and how they signal that failure to a human partner can determine whether the interaction turns into collaboration. Prior work on human–robot interaction has studied nonverbal help-seeking and social gaze separately, but rarely compares gaze against a matched verbal failure signal inside a live, real-time embodied search task. We present an embodied dialogue system, built on the Retico incremental processing framework, where the Cozmo robot searches for a specified object and signals failure either verbally or through gaze towards the human partner. We first compare a rule-based planner against a vision-language model (VLM) planner that reasons over scene semantics, finding that the VLM planner succeeds far more often (87.2% vs. 65.9%). We then test whether gaze can close this gap without adding reasoning capability to the rule-based planner. Adding gaze as the stuck signal raises success to 87.87%, matching the VLM planner, while a verbal stuck signal only raises it slightly (68.75%). Results further show that this effect is largely implicit: participants helped more in the gaze condition without consistently reporting that they felt invited to do so. Our findings suggest that gaze can substitute for reasoning capability a robot lacks, helping it elicit assistance from a human partner.</abstract>
<identifier type="citekey">manaseryan-etal-2026-looking</identifier>
<location>
<url>https://aclanthology.org/2026.mint-1.12/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>105</start>
<end>116</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Looking for Objects and Looking for Help: Robot Gaze Elicits Human Cooperation
%A Manaseryan, Anna
%A Bui, Thi Lan Anh
%A Kennington, Casey
%Y Ghaleb, Esam
%Y Takmaz, Ece
%Y Frassinelli, Diego
%Y Khaertdinov, Bulat
%Y Fernández, Raquel
%Y Yumak, Zerrin
%Y Ozyurek, Asli
%S Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-482-8
%F manaseryan-etal-2026-looking
%X Robots that search for objects on their own must decide what to do when the search fails, and how they signal that failure to a human partner can determine whether the interaction turns into collaboration. Prior work on human–robot interaction has studied nonverbal help-seeking and social gaze separately, but rarely compares gaze against a matched verbal failure signal inside a live, real-time embodied search task. We present an embodied dialogue system, built on the Retico incremental processing framework, where the Cozmo robot searches for a specified object and signals failure either verbally or through gaze towards the human partner. We first compare a rule-based planner against a vision-language model (VLM) planner that reasons over scene semantics, finding that the VLM planner succeeds far more often (87.2% vs. 65.9%). We then test whether gaze can close this gap without adding reasoning capability to the rule-based planner. Adding gaze as the stuck signal raises success to 87.87%, matching the VLM planner, while a verbal stuck signal only raises it slightly (68.75%). Results further show that this effect is largely implicit: participants helped more in the gaze condition without consistently reporting that they felt invited to do so. Our findings suggest that gaze can substitute for reasoning capability a robot lacks, helping it elicit assistance from a human partner.
%U https://aclanthology.org/2026.mint-1.12/
%P 105-116
Markdown (Informal)
[Looking for Objects and Looking for Help: Robot Gaze Elicits Human Cooperation](https://aclanthology.org/2026.mint-1.12/) (Manaseryan et al., MINT 2026)
ACL