@inproceedings{kim-etal-2020-arramon,
title = "{A}rra{M}on: A Joint Navigation-Assembly Instruction Interpretation Task in Dynamic Environments",
author = "Kim, Hyounghun and
Zala, Abhaysinh and
Burri, Graham and
Tan, Hao and
Bansal, Mohit",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.348",
doi = "10.18653/v1/2020.findings-emnlp.348",
pages = "3910--3927",
abstract = "For embodied agents, navigation is an important ability but not an isolated goal. Agents are also expected to perform specific tasks after reaching the target location, such as picking up objects and assembling them into a particular arrangement. We combine Vision-andLanguage Navigation, assembling of collected objects, and object referring expression comprehension, to create a novel joint navigation-and-assembly task, named ARRAMON. During this task, the agent (similar to a PokeMON GO player) is asked to find and collect different target objects one-by-one by navigating based on natural language (English) instructions in a complex, realistic outdoor environment, but then also ARRAnge the collected objects part-by-part in an egocentric grid-layout environment. To support this task, we implement a 3D dynamic environment simulator and collect a dataset with human-written navigation and assembling instructions, and the corresponding ground truth trajectories. We also filter the collected instructions via a verification stage, leading to a total of 7.7K task instances (30.8K instructions and paths). We present results for several baseline models (integrated and biased) and metrics (nDTW, CTC, rPOD, and PTC), and the large model-human performance gap demonstrates that our task is challenging and presents a wide scope for future work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2020-arramon">
<titleInfo>
<title>ArraMon: A Joint Navigation-Assembly Instruction Interpretation Task in Dynamic Environments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hyounghun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhaysinh</namePart>
<namePart type="family">Zala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Burri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>For embodied agents, navigation is an important ability but not an isolated goal. Agents are also expected to perform specific tasks after reaching the target location, such as picking up objects and assembling them into a particular arrangement. We combine Vision-andLanguage Navigation, assembling of collected objects, and object referring expression comprehension, to create a novel joint navigation-and-assembly task, named ARRAMON. During this task, the agent (similar to a PokeMON GO player) is asked to find and collect different target objects one-by-one by navigating based on natural language (English) instructions in a complex, realistic outdoor environment, but then also ARRAnge the collected objects part-by-part in an egocentric grid-layout environment. To support this task, we implement a 3D dynamic environment simulator and collect a dataset with human-written navigation and assembling instructions, and the corresponding ground truth trajectories. We also filter the collected instructions via a verification stage, leading to a total of 7.7K task instances (30.8K instructions and paths). We present results for several baseline models (integrated and biased) and metrics (nDTW, CTC, rPOD, and PTC), and the large model-human performance gap demonstrates that our task is challenging and presents a wide scope for future work.</abstract>
<identifier type="citekey">kim-etal-2020-arramon</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.348</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.348</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3910</start>
<end>3927</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ArraMon: A Joint Navigation-Assembly Instruction Interpretation Task in Dynamic Environments
%A Kim, Hyounghun
%A Zala, Abhaysinh
%A Burri, Graham
%A Tan, Hao
%A Bansal, Mohit
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F kim-etal-2020-arramon
%X For embodied agents, navigation is an important ability but not an isolated goal. Agents are also expected to perform specific tasks after reaching the target location, such as picking up objects and assembling them into a particular arrangement. We combine Vision-andLanguage Navigation, assembling of collected objects, and object referring expression comprehension, to create a novel joint navigation-and-assembly task, named ARRAMON. During this task, the agent (similar to a PokeMON GO player) is asked to find and collect different target objects one-by-one by navigating based on natural language (English) instructions in a complex, realistic outdoor environment, but then also ARRAnge the collected objects part-by-part in an egocentric grid-layout environment. To support this task, we implement a 3D dynamic environment simulator and collect a dataset with human-written navigation and assembling instructions, and the corresponding ground truth trajectories. We also filter the collected instructions via a verification stage, leading to a total of 7.7K task instances (30.8K instructions and paths). We present results for several baseline models (integrated and biased) and metrics (nDTW, CTC, rPOD, and PTC), and the large model-human performance gap demonstrates that our task is challenging and presents a wide scope for future work.
%R 10.18653/v1/2020.findings-emnlp.348
%U https://aclanthology.org/2020.findings-emnlp.348
%U https://doi.org/10.18653/v1/2020.findings-emnlp.348
%P 3910-3927
Markdown (Informal)
[ArraMon: A Joint Navigation-Assembly Instruction Interpretation Task in Dynamic Environments](https://aclanthology.org/2020.findings-emnlp.348) (Kim et al., Findings 2020)
ACL