{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/156325"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/156325","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Dialogue-driven Multi-Agent Activity Planning","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_html":"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_has_math":false,"creators":["Sonar, Anoopkumar S."],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Williams, Brian C."],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-22T22:21:04Z","subjects":[],"languages":[],"rights":["Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","Copyright retained by author(s)"],"rights_urls":["https://creativecommons.org/licenses/by-nc-nd/4.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/156325","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Williams, Brian C."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Sonar, Anoopkumar S."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-08-21T18:56:54Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-08-21T18:56:54Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Science in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://creativecommons.org/licenses/by-nc-nd/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/156325"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Dialogue-driven Multi-Agent Activity Planning"]}]}],"canonical_facts":{"dc:contributor.advisor":["Williams, Brian C."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Sonar, Anoopkumar S."],"dc:date.accessioned":["2024-08-21T18:56:54Z"],"dc:date.available":["2024-08-21T18:56:54Z"],"dc:date.issued":["2024-05"],"dc:description.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."],"dc:description.degree":["S.M."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/156325"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","Copyright retained by author(s)"],"dc:rights.uri":["https://creativecommons.org/licenses/by-nc-nd/4.0/"],"dc:title":["Dialogue-driven Multi-Agent Activity Planning"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Science in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:04Z"}