{"id":"https://openalex.org/W4413945360","doi":"https://doi.org/10.1109/icra55743.2025.11128677","title":"Socratic Planner: Self-QA-Based Zero-Shot Planning for Embodied Instruction Following","display_name":"Socratic Planner: Self-QA-Based Zero-Shot Planning for Embodied Instruction Following","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413945360","doi":"https://doi.org/10.1109/icra55743.2025.11128677"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081281228","display_name":"Suyeon Shin","orcid":"https://orcid.org/0000-0002-0780-4963"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Suyeon Shin","raw_affiliation_strings":["AI Institute, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104287354","display_name":"Sujin Jeon","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sujin Jeon","raw_affiliation_strings":["AI Institute, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349762","display_name":"Jung-Hyun Kim","orcid":"https://orcid.org/0000-0002-3328-4404"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junghyun Kim","raw_affiliation_strings":["AI Institute, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022061514","display_name":"Gi-Cheon Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gi-Cheon Kang","raw_affiliation_strings":["AI Institute, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109907976","display_name":"Byoung-Tak Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byoung-Tak Zhang","raw_affiliation_strings":["AI Institute, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16217","last_page":"16224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10533","display_name":"Teaching and Learning Programming","score":0.8831999897956848,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10533","display_name":"Teaching and Learning Programming","score":0.8831999897956848,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11299","display_name":"Problem and Project Based Learning","score":0.8090000152587891,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.8120981454849243},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.8040992021560669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6947112083435059},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5971450209617615},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.574247419834137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43341511487960815},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4028027057647705}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.8120981454849243},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.8040992021560669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6947112083435059},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5971450209617615},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.574247419834137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43341511487960815},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4028027057647705},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G638345476","display_name":null,"funder_award_id":"RS-2021-II212068-AIHub/10%,RS-2021-II211343-GSAI/15%,2022-0-00951-LBA/15%,2022-0-00953-PICA/20%","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G785413685","display_name":null,"funder_award_id":"RS-2024-00423940/10%","funder_id":"https://openalex.org/F4320334879","funder_display_name":"Korea Evaluation Institute of Industrial Technology"},{"id":"https://openalex.org/G8658812613","display_name":null,"funder_award_id":"RS-2024-00353991/20%,RS-2023-00274280/10%","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320334879","display_name":"Korea Evaluation Institute of Industrial Technology","ror":"https://ror.org/03z9cwa38"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2962684798","https://openalex.org/W3034758614","https://openalex.org/W3173781631","https://openalex.org/W3188987547","https://openalex.org/W3198840025","https://openalex.org/W4214700710","https://openalex.org/W4285306713","https://openalex.org/W4312436794","https://openalex.org/W4383108457","https://openalex.org/W4385571831","https://openalex.org/W4390873374","https://openalex.org/W4390874280","https://openalex.org/W4408918322"],"related_works":["https://openalex.org/W2380179524","https://openalex.org/W4283365723","https://openalex.org/W2963001125","https://openalex.org/W2091233881","https://openalex.org/W2352366064","https://openalex.org/W4250820896","https://openalex.org/W2124102101","https://openalex.org/W4250305970","https://openalex.org/W1484550171","https://openalex.org/W1570928019"],"abstract_inverted_index":{"Embodied":[0],"Instruction":[1],"Following":[2],"(EIF)":[3],"is":[4,26],"the":[5,47,73,89,120,123,132],"task":[6,28],"of":[7,85,122],"executing":[8,88],"natural":[9],"language":[10],"instructions":[11],"by":[12,72],"navigating":[13],"and":[14,70],"interacting":[15],"with":[16,39],"objects":[17],"in":[18,24,79,140],"interactive":[19],"environments.":[20],"A":[21],"key":[22],"challenge":[23],"EIF":[25],"compositional":[27],"planning,":[29],"typically":[30],"addressed":[31],"through":[32,113,153],"supervised":[33],"learning":[34,38],"or":[35],"few-shot":[36],"in-context":[37],"labeled":[40],"data.":[41],"To":[42],"this":[43],"end,":[44],"we":[45],"introduce":[46],"Socratic":[48,65,103,124],"Planner,":[49,125],"a":[50,83,114,156],"self-QA-based":[51],"zero-shot":[52],"planning":[53,129],"method":[54],"that":[55,143],"infers":[56],"an":[57,91],"appropriate":[58],"plan":[59],"without":[60],"any":[61],"further":[62,148],"training.":[63],"The":[64,102],"Planner":[66,104],"first":[67],"facilitates":[68],"self-questioning":[69],"answering":[71],"Large":[74],"Language":[75],"Model":[76],"(LLM),":[77],"which":[78],"turn":[80],"helps":[81],"generate":[82],"sequence":[84],"subgoals.":[86],"While":[87],"subgoals,":[90],"embodied":[92],"agent":[93],"may":[94],"encounter":[95],"unexpected":[96],"situations,":[97],"such":[98],"as":[99],"unforeseen":[100],"obstacles.":[101],"then":[105],"adjusts":[106],"plans":[107],"based":[108],"on":[109,131,155],"dense":[110],"visual":[111],"feedback":[112],"visuallygrounded":[115],"re-planning":[116],"mechanism.":[117],"Experiments":[118],"demonstrate":[119,149],"effectiveness":[121],"outperforming":[126],"current":[127],"state-of-the-art":[128],"models":[130],"ALFRED":[133],"benchmark":[134],"across":[135],"all":[136],"metrics,":[137],"particularly":[138],"excelling":[139],"long-horizon":[141,160],"tasks":[142],"demand":[144],"complex":[145],"inference.":[146],"We":[147],"its":[150],"real-world":[151],"applicability":[152],"deployment":[154],"physical":[157],"robot":[158],"for":[159],"tasks.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}