{"id":"https://openalex.org/W4415707856","doi":"https://doi.org/10.1109/icme59968.2025.11208991","title":"Text to Trajectory: Enhancing and Evaluating LLMs for Embodied Task Planning","display_name":"Text to Trajectory: Enhancing and Evaluating LLMs for Embodied Task Planning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707856","doi":"https://doi.org/10.1109/icme59968.2025.11208991"},"language":"en","primary_location":{"id":"doi:10.1109/icme59968.2025.11208991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208991","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","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/A5033478372","display_name":"Yihan Tang","orcid":"https://orcid.org/0000-0002-3971-2190"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yihan Tang","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101911686","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0002-8699-7256"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037627177","display_name":"Ruotao Xu","orcid":"https://orcid.org/0000-0002-5277-9859"},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruotao Xu","raw_affiliation_strings":["Institute of Super Robotics(Huangpu),Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Super Robotics(Huangpu),Guangzhou,China","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053838315","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0001-9136-195X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101884230","display_name":"Si Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Wu","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112791575","display_name":"Patrick Le Callet","orcid":null},"institutions":[{"id":"https://openalex.org/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrick Le Callet","raw_affiliation_strings":["Nantes Université,Nantes,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nantes Université,Nantes,France","institution_ids":["https://openalex.org/I97188460"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5033478372"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28877553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6862000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6862000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.04520000144839287,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.02160000056028366,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.8208000063896179},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7674999833106995},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.5406000018119812},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4982999861240387},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4860999882221222},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4593000113964081},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4009999930858612},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3846000134944916}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.8208000063896179},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7674999833106995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6072999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5473999977111816},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.5406000018119812},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4982999861240387},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4896000027656555},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4860999882221222},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4593000113964081},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3846000134944916},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.36169999837875366},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.311599999666214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31119999289512634},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.30399999022483826},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.28360000252723694},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.28220000863075256},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.2705000042915344},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.2563000023365021}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme59968.2025.11208991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208991","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05579492v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05579492","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME), Jun 2025, Nantes, France. pp.1-6, ⟨10.1109/ICME59968.2025.11208991⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334111","display_name":"Innovation Fund","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2083195487","https://openalex.org/W2506483933","https://openalex.org/W2799002257","https://openalex.org/W2963626623","https://openalex.org/W2963800628","https://openalex.org/W2964029788","https://openalex.org/W2979727876","https://openalex.org/W3034758614","https://openalex.org/W4214700710","https://openalex.org/W4382202802","https://openalex.org/W4390874280","https://openalex.org/W4398138749"],"related_works":[],"abstract_inverted_index":{"The":[0],"increasing":[1],"demand":[2],"for":[3,29],"effective":[4],"human-machine":[5],"interaction":[6],"highlights":[7],"the":[8,21,57,61,75,85,93,131],"importance":[9],"of":[10,23,67,77,87],"integrating":[11],"natural":[12],"language":[13],"processing":[14],"with":[15,46,56],"robotics":[16],"technology.":[17],"This":[18],"paper":[19],"addresses":[20],"challenges":[22],"using":[24],"Large":[25],"Language":[26],"Models":[27],"(LLMs)":[28],"embodied":[30,88,134],"task":[31,89,127,135],"planning":[32],"in":[33,121,133],"complex":[34],"environments.":[35],"We":[36],"propose":[37],"a":[38,47,98],"comprehensive":[39,65],"framework":[40,117],"that":[41,102],"combines":[42],"environmental-aware":[43],"LLM":[44],"fine-tuning":[45],"novel":[48],"Stepwise":[49],"Beam":[50],"Search":[51],"(SBS)":[52],"strategy.":[53],"In":[54],"conjunction":[55],"environmentally":[58],"enhanced":[59],"LLM,":[60],"SBS":[62],"strategy":[63],"facilitates":[64],"exploration":[66],"both":[68,122],"token-level":[69],"and":[70,126],"step-level":[71],"search":[72,80],"spaces,":[73],"overcoming":[74],"limitations":[76],"conventional":[78],"greedy":[79],"methods.":[81],"Additionally,":[82],"to":[83,106],"evaluate":[84],"effectiveness":[86],"planning,":[90],"we":[91],"introduce":[92],"Trajectory":[94],"Match":[95],"Score":[96],"(TMS),":[97],"robust":[99],"evaluation":[100],"metric":[101],"leverages":[103],"state-based":[104],"simulation":[105],"assess":[107],"plan":[108,123],"success.":[109],"Through":[110],"extensive":[111],"experiments":[112],"on":[113],"standard":[114],"benchmarks,":[115],"our":[116],"demonstrates":[118],"substantial":[119],"improvements":[120],"generation":[124],"quality":[125],"success":[128],"rates,":[129],"advancing":[130],"state-of-the-art":[132],"planning.":[136]},"counts_by_year":[],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-30T00:00:00"}