2026-09-19T16:59:16Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1180512023-08-04T11:48:05Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Antonio Torralba.
Puig Fernandez, Xavier(Francesc Xavier)
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2018-09-17T15:55:22Z
2018-09-17T15:55:22Z
2018
2018
http://hdl.handle.net/1721.1/118051
1051460096
Thesis: S.M. in Computer Science and Engineering, Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 53-55).
In order to learn to perform complex activities, autonomous agents need to know the sequences of actions needed to reach a given task. In this thesis, we propose to use programs, i.e., sequences of atomic actions and interactions, as a high level representation of complex tasks. Programs are interesting because they provide a non-ambiguous representation of a task, and allow agents to execute them. However, nowadays, there is no database providing this type of information. Towards this goal, we first crowd-source programs for a variety of activities that happen in people's homes, via a game-like interface used for teaching kids how to code. Using the collected dataset, we show how we can learn to extract programs directly from natural language descriptions or from videos. We then implement the most common atomic (inter)actions in the Unity3D game engine, and use our programs to "drive" an artificial agent to execute tasks in a simulated household environment. Our VirtualHome simulator allows us to create a large activity video dataset with rich ground-truth, enabling training and testing of video understanding models. We further showcase examples of our agent performing tasks in our VirtualHome based on language descriptions.
by Xavier Puig Fernandez.
S.M. in Computer Science and Engineering
55 pages
eng
Massachusetts Institute of Technology
MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
VirtualHome : simulating household activities via programs
Virtual Home : simulating household activities via programs
Simulating household activities via programs
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="2b59c943-8865-42be-9114-0ff6b64e78a2">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>VirtualHome : simulating household activities via programs</Title>
<Subtitle>Virtual Home : simulating household activities via programs</Subtitle>
<Subtitle>Simulating household activities via programs</Subtitle>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2018</PublicationDate>
<Authors>
<Author>
<DisplayName>Puig Fernandez, Xavier(Francesc Xavier)</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>In order to learn to perform complex activities, autonomous agents need to know the sequences of actions needed to reach a given task. In this thesis, we propose to use programs, i.e., sequences of atomic actions and interactions, as a high level representation of complex tasks. Programs are interesting because they provide a non-ambiguous representation of a task, and allow agents to execute them. However, nowadays, there is no database providing this type of information. Towards this goal, we first crowd-source programs for a variety of activities that happen in people's homes, via a game-like interface used for teaching kids how to code. Using the collected dataset, we show how we can learn to extract programs directly from natural language descriptions or from videos. We then implement the most common atomic (inter)actions in the Unity3D game engine, and use our programs to "drive" an artificial agent to execute tasks in a simulated household environment. Our VirtualHome simulator allows us to create a large activity video dataset with rich ground-truth, enabling training and testing of video understanding models. We further showcase examples of our agent performing tasks in our VirtualHome based on language descriptions.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>