{"id":"https://openalex.org/W4407247586","doi":"https://doi.org/10.1109/tcds.2025.3539665","title":"Where To Learn: Embodied Perception Learning Planned by Vision-Language Models","display_name":"Where To Learn: Embodied Perception Learning Planned by Vision-Language Models","publication_year":2025,"publication_date":"2025-02-07","ids":{"openalex":"https://openalex.org/W4407247586","doi":"https://doi.org/10.1109/tcds.2025.3539665"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2025.3539665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3539665","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-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":null,"display_name":"Juan Wang","orcid":"https://orcid.org/0000-0002-8241-8691"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Juan Wang","raw_affiliation_strings":["Department of Computer Science and Technology and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101833400","display_name":"Di Guo","orcid":"https://orcid.org/0000-0002-9816-0103"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Guo","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijin, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijin, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":null,"display_name":"Huaping Liu","orcid":"https://orcid.org/0000-0002-4042-6044"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaping Liu","raw_affiliation_strings":["Department of Computer Science and Technology and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75871665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"17","issue":"5","first_page":"1050","last_page":"1060"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5593000054359436,"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":0.5593000054359436,"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":0.8518965244293213},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8103417158126831},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6849313974380493},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5466582775115967},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.4374852776527405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3604426980018616},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.35922473669052124},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3231850564479828},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15616706013679504}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.8518965244293213},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8103417158126831},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6849313974380493},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5466582775115967},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.4374852776527405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3604426980018616},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.35922473669052124},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3231850564479828},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15616706013679504},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2025.3539665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3539665","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G3627598068","display_name":null,"funder_award_id":"62273054","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":26,"referenced_works":["https://openalex.org/W2889805803","https://openalex.org/W3024048225","https://openalex.org/W3107575247","https://openalex.org/W3171996075","https://openalex.org/W3174702694","https://openalex.org/W4226036061","https://openalex.org/W4226462773","https://openalex.org/W4283786914","https://openalex.org/W4285507550","https://openalex.org/W4292603841","https://openalex.org/W4379930655","https://openalex.org/W4383108417","https://openalex.org/W4387449009","https://openalex.org/W4389666115","https://openalex.org/W4390874280","https://openalex.org/W4391627003","https://openalex.org/W4391695316","https://openalex.org/W4392908117","https://openalex.org/W4395112928","https://openalex.org/W4399240167","https://openalex.org/W4400059351","https://openalex.org/W4401969036","https://openalex.org/W4403878234","https://openalex.org/W4405787555","https://openalex.org/W4408841099","https://openalex.org/W4411244521"],"related_works":["https://openalex.org/W1592154258","https://openalex.org/W1601503673","https://openalex.org/W1527882169","https://openalex.org/W4388039923","https://openalex.org/W2096246921","https://openalex.org/W2005500833","https://openalex.org/W2145935766","https://openalex.org/W2075610150","https://openalex.org/W2136562935","https://openalex.org/W2513760693"],"abstract_inverted_index":{"Embodied":[0],"learning":[1,17,23,71,99],"plays":[2],"a":[3],"crucial":[4],"role":[5],"in":[6,127],"transferring":[7],"self-learning":[8],"agents":[9],"to":[10,12,27,56,95,116,120,138,154],"adapt":[11],"the":[13,46,54,58,61,93,97,118,124,146,160,166,172],"environment.":[14],"Existing":[15],"embodied":[16,70,98],"methods":[18],"primarily":[19],"rely":[20],"on":[21],"reinforcement":[22],"(RL)":[24],"exploration":[25,39],"policy":[26],"collect":[28,123,155],"inaccurate":[29],"perceptual":[30,35,143],"result":[31],"samples":[32,126,156],"for":[33,48,51,174],"improving":[34],"capabilities.":[36],"However,":[37],"RL-based":[38],"policies":[40],"encounter":[41],"several":[42],"challenges":[43],"such":[44],"as":[45,78],"need":[47,173],"substantial":[49],"data":[50],"training":[52],"and":[53,83,104,122,145],"struggle":[55],"keep":[57],"diversity":[59],"of":[60,92,130,168],"collected":[62],"samples.":[63],"In":[64],"this":[65],"article,":[66],"we":[67],"propose":[68],"an":[69,135],"method":[72,88],"that":[73,141,157],"employs":[74,89],"vision-language":[75],"models":[76],"(VLMs)":[77],"task":[79,100],"planners,":[80,82],"code":[81],"path":[84],"planners.":[85],"Specifically,":[86],"our":[87,169],"layout":[90],"knowledge":[91],"VLMs":[94,133],"decompose":[96],"into":[101,109],"multiple":[102],"subtasks":[103],"then":[105],"convert":[106],"each":[107],"subtask":[108],"executable":[110],"code,":[111],"which":[112],"will":[113,148],"be":[114],"executed":[115],"guide":[117],"agent":[119,147],"explore":[121,149],"diverse":[125],"different":[128],"types":[129],"rooms.":[131],"Additionally,":[132],"incorporate":[134],"external":[136],"database":[137],"identify":[139],"regions":[140,153],"enhance":[142],"capabilities,":[144],"these":[150],"poor":[151],"perception":[152,161],"can":[158],"improve":[159],"performance.":[162],"Experimental":[163],"results":[164],"demonstrate":[165],"effectiveness":[167],"approach":[170],"without":[171],"additional":[175],"training.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}