{"id":"https://openalex.org/W4403534685","doi":"https://doi.org/10.1109/icarm62033.2024.10715821","title":"Learning Instruction-Guided Manipulation Affordance via Large Models for Embodied Robotic Tasks*","display_name":"Learning Instruction-Guided Manipulation Affordance via Large Models for Embodied Robotic Tasks*","publication_year":2024,"publication_date":"2024-07-08","ids":{"openalex":"https://openalex.org/W4403534685","doi":"https://doi.org/10.1109/icarm62033.2024.10715821"},"language":"en","primary_location":{"id":"doi:10.1109/icarm62033.2024.10715821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarm62033.2024.10715821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Advanced Robotics and Mechatronics (ICARM)","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/A5086871465","display_name":"Dayou Li","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dayou Li","raw_affiliation_strings":["Shandong University,School of Control Science and Engineering,Jinan,China,250061"],"affiliations":[{"raw_affiliation_string":"Shandong University,School of Control Science and Engineering,Jinan,China,250061","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109792804","display_name":"Chenkun Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenkun Zhao","raw_affiliation_strings":["Shandong University,School of Control Science and Engineering,Jinan,China,250061"],"affiliations":[{"raw_affiliation_string":"Shandong University,School of Control Science and Engineering,Jinan,China,250061","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070097565","display_name":"Shuo Yang","orcid":"https://orcid.org/0000-0002-3126-8021"},"institutions":[{"id":"https://openalex.org/I4210161528","display_name":"Qilu Hospital of Shandong University","ror":"https://ror.org/056ef9489","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210161528"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Yang","raw_affiliation_strings":["Qilu Hospital of Shandong University,Jinan,China,250012"],"affiliations":[{"raw_affiliation_string":"Qilu Hospital of Shandong University,Jinan,China,250012","institution_ids":["https://openalex.org/I4210161528"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101514629","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0002-5637-8577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Meituan,Beijing,China,100102"],"affiliations":[{"raw_affiliation_string":"Meituan,Beijing,China,100102","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100724411","display_name":"Yibin Li","orcid":"https://orcid.org/0000-0002-5906-5074"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibin Li","raw_affiliation_strings":["Shandong University,School of Control Science and Engineering,Jinan,China,250061"],"affiliations":[{"raw_affiliation_string":"Shandong University,School of Control Science and Engineering,Jinan,China,250061","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100756634","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-4960-3190"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Shandong University,School of Control Science and Engineering,Jinan,China,250061"],"affiliations":[{"raw_affiliation_string":"Shandong University,School of Control Science and Engineering,Jinan,China,250061","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5086871465"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":0.3495,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60507829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"662","last_page":"667"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9807999730110168,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9807999730110168,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9797000288963318,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.9282946586608887},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.9072567224502563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7306464314460754},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6624284982681274},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.43643203377723694},{"id":"https://openalex.org/keywords/cognitive-robotics","display_name":"Cognitive robotics","score":0.4190193712711334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33970868587493896}],"concepts":[{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.9282946586608887},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.9072567224502563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7306464314460754},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6624284982681274},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.43643203377723694},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.4190193712711334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33970868587493896}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icarm62033.2024.10715821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarm62033.2024.10715821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Advanced Robotics and Mechatronics (ICARM)","raw_type":"proceedings-article"}],"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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2475287302","https://openalex.org/W2891177506","https://openalex.org/W2962793652","https://openalex.org/W2963092423","https://openalex.org/W3006398608","https://openalex.org/W3120441392","https://openalex.org/W3133699737","https://openalex.org/W3199003182","https://openalex.org/W3205420310","https://openalex.org/W4224912544","https://openalex.org/W4238155858","https://openalex.org/W4306820534","https://openalex.org/W4312933868","https://openalex.org/W4313026212","https://openalex.org/W4323767275","https://openalex.org/W4362510460","https://openalex.org/W4366196888","https://openalex.org/W4383108457","https://openalex.org/W4383108836","https://openalex.org/W4385008474","https://openalex.org/W4385430538","https://openalex.org/W4386057725","https://openalex.org/W4386076215","https://openalex.org/W4388660746","https://openalex.org/W4389363803","https://openalex.org/W4389667233","https://openalex.org/W4390874280","https://openalex.org/W4390874575","https://openalex.org/W4404612908","https://openalex.org/W6785308759","https://openalex.org/W6791353385","https://openalex.org/W6801810553","https://openalex.org/W6810640255","https://openalex.org/W6840155194","https://openalex.org/W6846007759","https://openalex.org/W6846020498","https://openalex.org/W6850787431","https://openalex.org/W6851366896","https://openalex.org/W6851932778","https://openalex.org/W6854781572","https://openalex.org/W6855158220","https://openalex.org/W6858547910"],"related_works":["https://openalex.org/W1570928019","https://openalex.org/W2068486122","https://openalex.org/W2044346275","https://openalex.org/W2964506265","https://openalex.org/W2513760693","https://openalex.org/W2354934853","https://openalex.org/W2169574110","https://openalex.org/W2012344311","https://openalex.org/W381977300","https://openalex.org/W4252032091"],"abstract_inverted_index":{"We":[0,107],"study":[1],"the":[2,18,23,29,34,44,50,63,67,128,139],"task":[3],"of":[4,33,66,89,120,130,146],"language":[5,24,45,51,74,101,172],"instruction-guided":[6,90],"robotic":[7,91],"manipulation,":[8],"in":[9,59],"which":[10,47,114],"an":[11],"embodied":[12],"robot":[13],"is":[14],"supposed":[15],"to":[16,137,166],"manipulate":[17],"target":[19,35],"objects":[20,170],"based":[21],"on":[22,104],"instructions.":[25,75,143,173],"In":[26,76],"previous":[27],"studies,":[28],"predicted":[30],"manipulation":[31,54,64,92],"regions":[32,65],"object":[36,69],"typically":[37],"do":[38],"not":[39],"change":[40,71],"with":[41,127,157,168],"specification":[42],"from":[43,98],"instructions,":[46],"means":[48],"that":[49,150],"perception":[52],"and":[53,100,171],"prediction":[55],"are":[56],"separate.":[57],"However,":[58],"human":[60],"behavioral":[61],"patterns,":[62],"same":[68],"will":[70],"for":[72,85,123],"different":[73],"this":[77],"paper,":[78],"we":[79],"propose":[80],"Instruction-Guided":[81],"Affordance":[82],"Net":[83],"(IGANet)":[84],"predicting":[86],"affordance":[87],"maps":[88],"tasks":[93,140],"by":[94,142],"utilizing":[95],"powerful":[96],"priors":[97],"vision":[99],"encoders":[102],"pre-trained":[103],"large-scale":[105],"datasets.":[106],"develop":[108],"a":[109,117],"Vison-Language-Models(VLMs)-based":[110],"data":[111,121],"augmentation":[112],"pipeline,":[113],"can":[115,133,153,163],"generate":[116],"large":[118],"amount":[119],"automatically":[122],"model":[124,162],"training.":[125],"Besides,":[126],"help":[129],"Large-Language-Models(LLMs),":[131],"actions":[132],"be":[134],"effectively":[135],"executed":[136],"finish":[138],"defined":[141],"A":[144],"series":[145],"real-world":[147],"experiments":[148],"revealed":[149],"our":[151,161],"method":[152],"achieve":[154],"better":[155,165],"performance":[156],"generated":[158],"data.":[159],"Moreover,":[160],"generalize":[164],"scenarios":[167],"unseen":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}