@inproceedings{cao-etal-2022-goal,
title = "Goal-oriented Vision-and-Dialog Navigation via Reinforcement Learning",
author = "Cao, Yan and
Lu, Keting and
DeFazio, David and
Zhang, Shiqi",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.327/",
doi = "10.18653/v1/2022.findings-emnlp.327",
pages = "4473--4482",
abstract = "Vision-and-dialog navigation is a recent benchmark for evaluating the AI capabilities of perception, interaction, and decision making. While existing methods developed for this benchmark have demonstrated great successes, they mostly rely on large datasets, where data collection can be a challenge, and the learned policies are not adaptive to domain changes. In this paper, we focus on a new problem, referred to as goal-oriented vision-and-dialog navigation (GVDN), where an agent uses reinforcement learning techniques to compute dialog-navigation policies from trial and error. A robot conducts visual navigation to locate target objects, and can talk to a remote human operator as needed. Our remote human is able to provide guidance on navigation only if the robot correctly conveys its location through dialog. Experiments have been conducted using photo-realistic simulation environments. Results suggest that, our agent outperforms competitive baselines in success rate."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cao-etal-2022-goal">
<titleInfo>
<title>Goal-oriented Vision-and-Dialog Navigation via Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keting</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">DeFazio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiqi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Vision-and-dialog navigation is a recent benchmark for evaluating the AI capabilities of perception, interaction, and decision making. While existing methods developed for this benchmark have demonstrated great successes, they mostly rely on large datasets, where data collection can be a challenge, and the learned policies are not adaptive to domain changes. In this paper, we focus on a new problem, referred to as goal-oriented vision-and-dialog navigation (GVDN), where an agent uses reinforcement learning techniques to compute dialog-navigation policies from trial and error. A robot conducts visual navigation to locate target objects, and can talk to a remote human operator as needed. Our remote human is able to provide guidance on navigation only if the robot correctly conveys its location through dialog. Experiments have been conducted using photo-realistic simulation environments. Results suggest that, our agent outperforms competitive baselines in success rate.</abstract>
<identifier type="citekey">cao-etal-2022-goal</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.327</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.327/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>4473</start>
<end>4482</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Goal-oriented Vision-and-Dialog Navigation via Reinforcement Learning
%A Cao, Yan
%A Lu, Keting
%A DeFazio, David
%A Zhang, Shiqi
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F cao-etal-2022-goal
%X Vision-and-dialog navigation is a recent benchmark for evaluating the AI capabilities of perception, interaction, and decision making. While existing methods developed for this benchmark have demonstrated great successes, they mostly rely on large datasets, where data collection can be a challenge, and the learned policies are not adaptive to domain changes. In this paper, we focus on a new problem, referred to as goal-oriented vision-and-dialog navigation (GVDN), where an agent uses reinforcement learning techniques to compute dialog-navigation policies from trial and error. A robot conducts visual navigation to locate target objects, and can talk to a remote human operator as needed. Our remote human is able to provide guidance on navigation only if the robot correctly conveys its location through dialog. Experiments have been conducted using photo-realistic simulation environments. Results suggest that, our agent outperforms competitive baselines in success rate.
%R 10.18653/v1/2022.findings-emnlp.327
%U https://aclanthology.org/2022.findings-emnlp.327/
%U https://doi.org/10.18653/v1/2022.findings-emnlp.327
%P 4473-4482
Markdown (Informal)
[Goal-oriented Vision-and-Dialog Navigation via Reinforcement Learning](https://aclanthology.org/2022.findings-emnlp.327/) (Cao et al., Findings 2022)
ACL