{"id":"https://openalex.org/W4390099692","doi":"https://doi.org/10.1109/robio58561.2023.10355013","title":"A Modular Framework for Robot Embodied Instruction Following by Large Language Model","display_name":"A Modular Framework for Robot Embodied Instruction Following by Large Language Model","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4390099692","doi":"https://doi.org/10.1109/robio58561.2023.10355013"},"language":"en","primary_location":{"id":"doi:10.1109/robio58561.2023.10355013","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio58561.2023.10355013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5100408802","display_name":"Long Li","orcid":"https://orcid.org/0000-0003-1973-8550"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Li","raw_affiliation_strings":["Tongji University,The School of Electronics and Information,Shanghai,China","The School of Electronics and Information, Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,The School of Electronics and Information,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"The School of Electronics and Information, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101789136","display_name":"Hongjun Zhou","orcid":"https://orcid.org/0000-0002-6256-2485"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjun Zhou","raw_affiliation_strings":["Tongji University,The School of Electronics and Information,Shanghai,China","The School of Electronics and Information, Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,The School of Electronics and Information,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"The School of Electronics and Information, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010299064","display_name":"Mingyu You","orcid":"https://orcid.org/0000-0003-2758-167X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu You","raw_affiliation_strings":["Tongji University,The School of Electronics and Information,Shanghai,China","The School of Electronics and Information, Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,The School of Electronics and Information,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"The School of Electronics and Information, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.1214,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47424422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"abs/1712.05474","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":1.0,"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":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9961000084877014,"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/computer-science","display_name":"Computer science","score":0.8492951989173889},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6769036054611206},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.654199481010437},{"id":"https://openalex.org/keywords/container","display_name":"Container (type theory)","score":0.626415491104126},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5638904571533203},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5436853170394897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5237845778465271},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5155453681945801},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4761488437652588},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.44671863317489624},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.41585949063301086},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41322970390319824},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21726146340370178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8492951989173889},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6769036054611206},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.654199481010437},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.626415491104126},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5638904571533203},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5436853170394897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5237845778465271},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5155453681945801},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4761488437652588},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.44671863317489624},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41585949063301086},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41322970390319824},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21726146340370178},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio58561.2023.10355013","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio58561.2023.10355013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1999244633","https://openalex.org/W2965373594","https://openalex.org/W3034758614","https://openalex.org/W3112356180","https://openalex.org/W3173781631","https://openalex.org/W3188987547","https://openalex.org/W3214642103","https://openalex.org/W4214700710","https://openalex.org/W4285306713","https://openalex.org/W4286905705","https://openalex.org/W4287026640","https://openalex.org/W4287079536","https://openalex.org/W4292779060","https://openalex.org/W4293566037","https://openalex.org/W4308614384","https://openalex.org/W6796581206","https://openalex.org/W6798219303","https://openalex.org/W6802203484","https://openalex.org/W6803039797"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W2326995835","https://openalex.org/W165915117","https://openalex.org/W2059402478","https://openalex.org/W2123347777","https://openalex.org/W4387804363","https://openalex.org/W2019547100","https://openalex.org/W2477150073","https://openalex.org/W2515493494"],"abstract_inverted_index":{"In":[0],"the":[1,7,18,27,39,62,117,131,157,184,212,216,228],"ALFRED":[2,158,217],"challenge":[3,12],"for":[4,83],"robot":[5,8,28,132],"simulation,":[6],"still":[9],"faces":[10],"a":[11,15,48,58,74,98,196],"to":[13,29,96,200],"schedule":[14],"task":[16,129],"in":[17,65,140,189,215],"embodied":[19],"instruction":[20],"following":[21,229],"(EIF)":[22],"tasks.":[23],"These":[24,171],"tasks":[25,56,139,155],"require":[26],"accurately":[30,136,182],"perceive":[31],"visual":[32,84,103],"features":[33],"and":[34,94,135,163,168,181,192,225],"understand":[35],"language":[36,52,86,104,124],"instructions.":[37,67],"However,":[38],"previous":[40],"approaches":[41],"typically":[42],"employed":[43],"end-to-end":[44],"structures":[45],"that":[46,174],"utilize":[47],"shallow":[49],"understanding":[50,60],"of":[51,61,166,179,186,198],"instructions,":[53,130],"while":[54,116],"EIF":[55,138],"demand":[57],"deeper":[59,123],"semantic":[63,88,108],"relationships":[64],"these":[66,70],"To":[68],"overcome":[69],"limitations,":[71],"we":[72],"propose":[73],"method":[75,80,176,209],"which":[76],"named":[77],"REIF.":[78],"The":[79,107],"incorporates":[81],"modules":[82],"perception,":[85],"understanding,":[87],"search,":[89,115],"closed":[90,118,187,206],"container":[91,119,188],"prediction,":[92],"navigation,":[93],"operation":[95],"form":[97],"modular":[99],"framework":[100,148],"based":[101],"on":[102,152],"multi-modal":[105],"learning.":[106],"search":[109],"module":[110,121],"supports":[111],"more":[112],"efficient":[113],"object":[114,204],"prediction":[120],"enables":[122],"understanding.":[125],"Through":[126],"learning":[127],"multiple":[128],"can":[133,193,221],"efficiently":[134,180],"complete":[137],"unseen":[141,153,190],"scenes":[142],"under":[143],"certain":[144],"step":[145],"lengths.":[146],"Our":[147,208],"performs":[149],"significantly":[150],"well":[151],"scene":[154],"within":[156,205],"benchmark,":[159],"achieving":[160],"state-of-the-art":[161],"accuracy":[162],"efficiency":[164],"rates":[165],"50.83%":[167],"23.06%":[169],"respectively.":[170],"results":[172,226],"demonstrate":[173],"our":[175,223],"is":[177],"capable":[178],"inferring":[183],"presence":[185],"scenes,":[191],"successfully":[194],"execute":[195],"series":[197],"actions":[199],"interact":[201],"with":[202],"target":[203],"container.":[207],"has":[210],"achieved":[211],"first":[213],"place":[214],"data-set":[218],"competition.":[219],"You":[220],"find":[222],"submissions":[224],"at":[227],"link:":[230],"https://leaderboard.allenai.org/alfred/submissions/public.":[231]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}