@inproceedings{krishnaswamy-etal-2022-voxworld,
title = "The {V}ox{W}orld Platform for Multimodal Embodied Agents",
author = "Krishnaswamy, Nikhil and
Pickard, William and
Cates, Brittany and
Blanchard, Nathaniel and
Pustejovsky, James",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.164",
pages = "1529--1541",
abstract = "We present a five-year retrospective on the development of the VoxWorld platform, first introduced as a multimodal platform for modeling motion language, that has evolved into a platform for rapidly building and deploying embodied agents with contextual and situational awareness, capable of interacting with humans in multiple modalities, and exploring their environments. In particular, we discuss the evolution from the theoretical underpinnings of the VoxML modeling language to a platform that accommodates both neural and symbolic inputs to build agents capable of multimodal interaction and hybrid reasoning. We focus on three distinct agent implementations and the functionality needed to accommodate all of them: Diana, a virtual collaborative agent; Kirby, a mobile robot; and BabyBAW, an agent who self-guides its own exploration of the world.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krishnaswamy-etal-2022-voxworld">
<titleInfo>
<title>The VoxWorld Platform for Multimodal Embodied Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikhil</namePart>
<namePart type="family">Krishnaswamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Pickard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brittany</namePart>
<namePart type="family">Cates</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Blanchard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a five-year retrospective on the development of the VoxWorld platform, first introduced as a multimodal platform for modeling motion language, that has evolved into a platform for rapidly building and deploying embodied agents with contextual and situational awareness, capable of interacting with humans in multiple modalities, and exploring their environments. In particular, we discuss the evolution from the theoretical underpinnings of the VoxML modeling language to a platform that accommodates both neural and symbolic inputs to build agents capable of multimodal interaction and hybrid reasoning. We focus on three distinct agent implementations and the functionality needed to accommodate all of them: Diana, a virtual collaborative agent; Kirby, a mobile robot; and BabyBAW, an agent who self-guides its own exploration of the world.</abstract>
<identifier type="citekey">krishnaswamy-etal-2022-voxworld</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.164</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1529</start>
<end>1541</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The VoxWorld Platform for Multimodal Embodied Agents
%A Krishnaswamy, Nikhil
%A Pickard, William
%A Cates, Brittany
%A Blanchard, Nathaniel
%A Pustejovsky, James
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F krishnaswamy-etal-2022-voxworld
%X We present a five-year retrospective on the development of the VoxWorld platform, first introduced as a multimodal platform for modeling motion language, that has evolved into a platform for rapidly building and deploying embodied agents with contextual and situational awareness, capable of interacting with humans in multiple modalities, and exploring their environments. In particular, we discuss the evolution from the theoretical underpinnings of the VoxML modeling language to a platform that accommodates both neural and symbolic inputs to build agents capable of multimodal interaction and hybrid reasoning. We focus on three distinct agent implementations and the functionality needed to accommodate all of them: Diana, a virtual collaborative agent; Kirby, a mobile robot; and BabyBAW, an agent who self-guides its own exploration of the world.
%U https://aclanthology.org/2022.lrec-1.164
%P 1529-1541
Markdown (Informal)
[The VoxWorld Platform for Multimodal Embodied Agents](https://aclanthology.org/2022.lrec-1.164) (Krishnaswamy et al., LREC 2022)
ACL
- Nikhil Krishnaswamy, William Pickard, Brittany Cates, Nathaniel Blanchard, and James Pustejovsky. 2022. The VoxWorld Platform for Multimodal Embodied Agents. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1529–1541, Marseille, France. European Language Resources Association.