2026-09-18T19:32:38Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1563252024-08-22T03:53:38Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Williams, Brian C.
Sonar, Anoopkumar S.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2024-08-21T18:56:54Z
2024-08-21T18:56:54Z
2024-05
2024-07-10T12:59:59.141Z
https://hdl.handle.net/1721.1/156325
https://orcid.org/0000-0003-0478-0254
A fundamental challenge in robotics is to build a general-purpose system with multiple agents that can perform a wide range of tasks based on specifications provided in natural language. This work presents a novel dialogue-driven activity planning framework for multiagent scenarios. We present a method that accepts commands from a user in natural language and translates it to an intermediate form called a state plan by leveraging large language models. We further experiment with chain-of-thought prompting to improve the translation from natural language to state plans. In conjunction with an action model, this state plan is utilized by a constraint-based generative planner called ctBurton which outputs a full grounded plan in the form of a state and control trajectory. We demonstrate the utility of our method across three different scenarios– a presentation system, search-and-rescue, and multi-agent assembly– along with experiments on its scalability.
S.M.
Massachusetts Institute of Technology
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Copyright retained by author(s)
https://creativecommons.org/licenses/by-nc-nd/4.0/
Dialogue-driven Multi-Agent Activity Planning
Thesis
application/pdf
Master
Master of Science in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="2cbbd11a-cbb2-43ea-943d-01c9d17d59a2">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Dialogue-driven Multi-Agent Activity Planning</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2024-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Sonar, Anoopkumar S.</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://creativecommons.org/licenses/by-nc-nd/4.0/</License>
<Abstract>A fundamental challenge in robotics is to build a general-purpose system with multiple agents that can perform a wide range of tasks based on specifications provided in natural language. This work presents a novel dialogue-driven activity planning framework for multiagent scenarios. We present a method that accepts commands from a user in natural language and translates it to an intermediate form called a state plan by leveraging large language models. We further experiment with chain-of-thought prompting to improve the translation from natural language to state plans. In conjunction with an action model, this state plan is utilized by a constraint-based generative planner called ctBurton which outputs a full grounded plan in the form of a state and control trajectory. We demonstrate the utility of our method across three different scenarios– a presentation system, search-and-rescue, and multi-agent assembly– along with experiments on its scalability.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>