{"id":"https://openalex.org/W4416750179","doi":"https://doi.org/10.1109/iros60139.2025.11246714","title":"TR-LLM: Integrating Trajectory Data for Scene-Aware LLM-Based Human Action Prediction","display_name":"TR-LLM: Integrating Trajectory Data for Scene-Aware LLM-Based Human Action Prediction","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750179","doi":"https://doi.org/10.1109/iros60139.2025.11246714"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5082334105","display_name":"Kojiro Takeyama","orcid":"https://orcid.org/0000-0002-7774-3342"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kojiro Takeyama","raw_affiliation_strings":["University of California Santa Barbara,Department of Computer Science,Santa Barbara,CA,USA,93106-5080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Santa Barbara,Department of Computer Science,Santa Barbara,CA,USA,93106-5080","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101533871","display_name":"Yimeng Liu","orcid":"https://orcid.org/0000-0002-6742-2908"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yimeng Liu","raw_affiliation_strings":["University of California Santa Barbara,Department of Computer Science,Santa Barbara,CA,USA,93106-5080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Santa Barbara,Department of Computer Science,Santa Barbara,CA,USA,93106-5080","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029380651","display_name":"Misha Sra","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Misha Sra","raw_affiliation_strings":["University of California Santa Barbara,Department of Computer Science,Santa Barbara,CA,USA,93106-5080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Santa Barbara,Department of Computer Science,Santa Barbara,CA,USA,93106-5080","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154570441"],"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":"18708","last_page":"18715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5153999924659729,"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":0.5153999924659729,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.16179999709129333,"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/T12290","display_name":"Human Motion and Animation","score":0.0723000019788742,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.707099974155426},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6726999878883362},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6018000245094299},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.39160001277923584},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.384799987077713},{"id":"https://openalex.org/keywords/compromise","display_name":"Compromise","score":0.34060001373291016},{"id":"https://openalex.org/keywords/human-behavior","display_name":"Human behavior","score":0.34040001034736633},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.3391999900341034}],"concepts":[{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.707099974155426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6868000030517578},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6726999878883362},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6018000245094299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5708000063896179},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4487999975681305},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.39160001277923584},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C46355384","wikidata":"https://www.wikidata.org/wiki/Q726686","display_name":"Compromise","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.3391999900341034},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.29249998927116394},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.25049999356269836},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2043417668","https://openalex.org/W2101032778","https://openalex.org/W2551531860","https://openalex.org/W2908501829","https://openalex.org/W3021065276","https://openalex.org/W3034938233","https://openalex.org/W3106884574","https://openalex.org/W3109717189","https://openalex.org/W3172615168","https://openalex.org/W3173599944","https://openalex.org/W3173655578","https://openalex.org/W3175928291","https://openalex.org/W3205786327","https://openalex.org/W4214555767","https://openalex.org/W4307475457","https://openalex.org/W4319299948","https://openalex.org/W4319300049","https://openalex.org/W4387835442","https://openalex.org/W4388744821","https://openalex.org/W4389665836","https://openalex.org/W4390872176","https://openalex.org/W4390873483","https://openalex.org/W4394625740","https://openalex.org/W4401415105","https://openalex.org/W4402660087","https://openalex.org/W4402716288","https://openalex.org/W4402727280","https://openalex.org/W4403446304","https://openalex.org/W4415800665","https://openalex.org/W4415821931","https://openalex.org/W4416750179"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"prediction":[1,123,129,151],"of":[2,79,171],"human":[3,23,72,80,136,181],"behavior":[4],"is":[5,155],"crucial":[6],"for":[7],"AI":[8],"systems":[9],"to":[10,49,111],"effectively":[11],"support":[12],"real-world":[13,116],"applications,":[14],"such":[15,30],"as":[16,31],"autonomous":[17],"robots":[18],"anticipating":[19,180],"and":[20,33,52,97,107,174,179],"assisting":[21],"with":[22,103,145],"tasks.":[24],"Real-world":[25],"scenarios":[26],"frequently":[27],"present":[28],"challenges":[29],"occlusions":[32],"incomplete":[34],"scene":[35,165],"observations,":[36],"which":[37],"can":[38],"compromise":[39],"predictive":[40],"accuracy.":[41],"Thus,":[42],"traditional":[43],"video-based":[44],"methods":[45],"often":[46],"struggle":[47,102],"due":[48],"limited":[50,164],"temporal":[51],"spatial":[53,95,108,117],"perspectives.":[54],"Large":[55],"Language":[56],"Models":[57],"(LLMs)":[58],"offer":[59],"a":[60,67,83,115,121],"promising":[61],"alternative.":[62],"Having":[63],"been":[64],"trained":[65,88],"on":[66,90],"large":[68],"text":[69,91],"corpus":[70],"describing":[71],"behaviors,":[73],"LLMs":[74],"likely":[75],"encode":[76],"plausible":[77],"sequences":[78],"actions":[81],"in":[82,114,158,177],"home":[84],"environment.":[85],"However,":[86],"LLMs,":[87],"primarily":[89],"data,":[92],"lack":[93],"inherent":[94],"awareness":[96],"real-time":[98],"environmental":[99],"perception.":[100],"They":[101],"understanding":[104,178],"physical":[105,132,175],"constraints":[106,133,176],"geometry.":[109],"Therefore,":[110],"be":[112],"effective":[113],"scenario,":[118],"we":[119],"propose":[120],"multimodal":[122],"framework":[124],"that":[125,141],"enhances":[126],"LLM-based":[127],"action":[128],"by":[130],"integrating":[131],"derived":[134],"from":[135],"trajectories.":[137],"Our":[138],"experiments":[139],"demonstrate":[140],"combining":[142],"LLM":[143,162],"predictions":[144],"trajectory":[146],"data":[147],"significantly":[148],"improves":[149],"overall":[150],"performance.":[152],"This":[153],"enhancement":[154],"particularly":[156],"notable":[157],"situations":[159],"where":[160],"the":[161,168],"receives":[163],"information,":[166],"highlighting":[167],"complementary":[169],"nature":[170],"linguistic":[172],"knowledge":[173],"behavior.Project":[182],"page:":[183],"https://sites.google.com/view/trllm\u0192usp=sharingGithub":[184],"repo:":[185],"https://github.com/kojirotakeyama/TR-LLM/blob/main/readme.md":[186]},"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":"2025-11-28T00:00:00"}