{"id":"https://openalex.org/W4405786400","doi":"https://doi.org/10.1109/iros58592.2024.10801446","title":"Polaris: Open-ended Interactive Robotic Manipulation via Syn2Real Visual Grounding and Large Language Models","display_name":"Polaris: Open-ended Interactive Robotic Manipulation via Syn2Real Visual Grounding and Large Language Models","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405786400","doi":"https://doi.org/10.1109/iros58592.2024.10801446"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5100417426","display_name":"Tianyu Wang","orcid":"https://orcid.org/0000-0002-6087-6376"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyu Wang","raw_affiliation_strings":["Fudan University,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100308160","display_name":"Haitao Lin","orcid":"https://orcid.org/0000-0001-7054-7915"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Lin","raw_affiliation_strings":["Fudan University,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034398235","display_name":"Jinhui Yu","orcid":"https://orcid.org/0000-0002-9946-4854"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junqiu Yu","raw_affiliation_strings":["Fudan University,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084959430","display_name":"Yanwei Fu","orcid":"https://orcid.org/0000-0002-6595-6893"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Fu","raw_affiliation_strings":["Fudan University,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100417426"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.0998,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79628018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"9676","last_page":"9683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9757999777793884,"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":0.9616000056266785,"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":0.7715988755226135},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4847964346408844},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.4841518998146057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42048409581184387},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.391085684299469},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33221879601478577},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.32892316579818726},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13110777735710144},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09574362635612488}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7715988755226135},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4847964346408844},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.4841518998146057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42048409581184387},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.391085684299469},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33221879601478577},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.32892316579818726},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13110777735710144},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09574362635612488}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320329902","display_name":"Shanghai Platform for Neuromorphic and AI Chip","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W2772449134","https://openalex.org/W2950069298","https://openalex.org/W2961368225","https://openalex.org/W2963669336","https://openalex.org/W2963892972","https://openalex.org/W2967820818","https://openalex.org/W2986303149","https://openalex.org/W3003205975","https://openalex.org/W3035198432","https://openalex.org/W3035398346","https://openalex.org/W3035624836","https://openalex.org/W3122520957","https://openalex.org/W3163945288","https://openalex.org/W3193686508","https://openalex.org/W3202459445","https://openalex.org/W3202538459","https://openalex.org/W3207832698","https://openalex.org/W4200578307","https://openalex.org/W4224912544","https://openalex.org/W4226321491","https://openalex.org/W4280533594","https://openalex.org/W4280586270","https://openalex.org/W4285102324","https://openalex.org/W4312296985","https://openalex.org/W4312604533","https://openalex.org/W4313027996","https://openalex.org/W4313189197","https://openalex.org/W4319036022","https://openalex.org/W4382366145","https://openalex.org/W4383066417","https://openalex.org/W4383108184","https://openalex.org/W4386066594","https://openalex.org/W4386320380","https://openalex.org/W4387764390","https://openalex.org/W4389665836","https://openalex.org/W4389666637","https://openalex.org/W4389667233","https://openalex.org/W4389667691","https://openalex.org/W4390872134","https://openalex.org/W4390874575","https://openalex.org/W4394828156","https://openalex.org/W4401905821","https://openalex.org/W4404612908","https://openalex.org/W6687484953","https://openalex.org/W6800425027","https://openalex.org/W6802625470","https://openalex.org/W6841115740","https://openalex.org/W6845804354","https://openalex.org/W6850343319","https://openalex.org/W6851775633","https://openalex.org/W6852157226","https://openalex.org/W6852884379","https://openalex.org/W6853702739","https://openalex.org/W6854738657","https://openalex.org/W6854929498","https://openalex.org/W6854942309","https://openalex.org/W6855500481","https://openalex.org/W6857844089"],"related_works":["https://openalex.org/W2021787609","https://openalex.org/W1537063595","https://openalex.org/W2097328689","https://openalex.org/W4234899305","https://openalex.org/W2379604501","https://openalex.org/W2373854414","https://openalex.org/W2574906695","https://openalex.org/W2522183581","https://openalex.org/W2954371137","https://openalex.org/W2120744156"],"abstract_inverted_index":{"This":[0,40,121,175],"paper":[1],"investigates":[2],"the":[3,6,38,43,48,54,97,109,141,162,184],"task":[4],"of":[5,23,28,143,165],"open-ended":[7],"interactive":[8,63],"robotic":[9,64],"manipulation":[10,52,65,135,173],"on":[11],"table-top":[12],"scenarios.":[13],"While":[14],"recent":[15],"Large":[16],"Language":[17],"Models":[18],"(LLMs)":[19],"enhance":[20],"robots'":[21],"comprehension":[22],"user":[24],"instructions,":[25],"their":[26,32],"lack":[27],"visual":[29],"grounding":[30],"constrains":[31],"ability":[33],"to":[34,46,106,133,153,179,181],"physically":[35],"interact":[36],"with":[37],"environment.":[39],"is":[41,85,130],"because":[42],"robot":[44],"needs":[45],"locate":[47],"target":[49,98],"object":[50,94],"for":[51,96,127,151],"within":[53],"physical":[55],"workspace.":[56],"To":[57],"this":[58],"end,":[59],"we":[60,112],"introduce":[61],"an":[62],"framework":[66,167],"called":[67],"Polaris,":[68],"which":[69],"integrates":[70],"perception":[71],"and":[72,129,147,170,188],"interaction":[73],"by":[74],"utilizing":[75],"GPT-4":[76],"alongside":[77],"grounded":[78,89],"vision":[79,90],"models.":[80],"For":[81],"precise":[82],"manipulation,":[83],"it":[84],"essential":[86],"that":[87],"such":[88],"models":[91],"produce":[92],"detailed":[93],"pose":[95,118],"object,":[99],"rather":[100],"than":[101],"merely":[102],"identifying":[103],"pixels":[104],"belonging":[105],"them":[107],"in":[108,168],"image.":[110],"Consequently,":[111],"propose":[113],"a":[114],"novel":[115],"Synthetic-to-Real":[116],"(Syn2Real)":[117],"estimation":[119],"pipeline.":[120],"pipeline":[122,146],"utilizes":[123],"rendered":[124],"synthetic":[125],"data":[126],"training":[128],"then":[131],"transferred":[132],"real-world":[134,138],"tasks.":[136,174],"The":[137],"performance":[139,164],"demonstrates":[140],"efficacy":[142],"our":[144,166],"proposed":[145],"underscores":[148],"its":[149,177],"potential":[150,178],"extension":[152],"more":[154],"general":[155],"categories.":[156],"Moreover,":[157],"real-robot":[158],"experiments":[159],"have":[160],"showcased":[161],"impressive":[163],"grasping":[169],"executing":[171],"multiple":[172],"indicates":[176],"generalize":[180],"scenarios":[182],"beyond":[183],"tabletop.":[185],"More":[186],"information":[187],"video":[189],"results":[190],"are":[191],"available":[192],"here:":[193],"https://star-uu-wang.github.io/Polaris/.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}