{"id":"https://openalex.org/W4210380813","doi":"https://doi.org/10.1109/lra.2022.3146955","title":"Language-Driven Robot Manipulation With Perspective Disambiguation and Placement Optimization","display_name":"Language-Driven Robot Manipulation With Perspective Disambiguation and Placement Optimization","publication_year":2022,"publication_date":"2022-01-31","ids":{"openalex":"https://openalex.org/W4210380813","doi":"https://doi.org/10.1109/lra.2022.3146955"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3146955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3146955","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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":"https://openalex.org/A5022463981","display_name":"Kaixiang Huang","orcid":"https://orcid.org/0000-0002-1256-153X"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaixiang Huang","raw_affiliation_strings":["School of Mechanical Engineering, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-1256-153X","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101948401","display_name":"Yuxuan Han","orcid":"https://orcid.org/0000-0003-0946-6141"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Han","raw_affiliation_strings":["School of Mechanical Engineering, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-0946-6141","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102799622","display_name":"Jinze Wu","orcid":"https://orcid.org/0000-0003-0268-6520"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinze Wu","raw_affiliation_strings":["School of Mechanical Engineering, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-0268-6520","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019272956","display_name":"Fang\u2010Zhou Qiu","orcid":"https://orcid.org/0000-0002-5459-2377"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangzhou Qiu","raw_affiliation_strings":["School of Mechanical Engineering, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5459-2377","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032136223","display_name":"Qing Tang","orcid":"https://orcid.org/0000-0002-1300-6394"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Tang","raw_affiliation_strings":["School of Mechanical Engineering, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-1300-6394","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5022463981"],"corresponding_institution_ids":["https://openalex.org/I24185976"],"apc_list":null,"apc_paid":null,"fwci":0.9184,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.74198911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"7","issue":"2","first_page":"4188","last_page":"4195"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9988999962806702,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.784554660320282},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.748836874961853},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6551390886306763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.59173983335495},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5347626805305481},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5307934880256653},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4953542947769165},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44279932975769043},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4392669200897217},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.43466097116470337},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.14722022414207458},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13461995124816895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784554660320282},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.748836874961853},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6551390886306763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.59173983335495},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5347626805305481},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5307934880256653},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4953542947769165},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44279932975769043},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4392669200897217},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.43466097116470337},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14722022414207458},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13461995124816895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2022.3146955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3146955","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W197179470","https://openalex.org/W1536085466","https://openalex.org/W1861492603","https://openalex.org/W1994616995","https://openalex.org/W2006354339","https://openalex.org/W2250539671","https://openalex.org/W2517194566","https://openalex.org/W2550322026","https://openalex.org/W2561715562","https://openalex.org/W2616986359","https://openalex.org/W2663904211","https://openalex.org/W2736923367","https://openalex.org/W2776323726","https://openalex.org/W2810720462","https://openalex.org/W2896457183","https://openalex.org/W2963150697","https://openalex.org/W2963349093","https://openalex.org/W2963683806","https://openalex.org/W2963735856","https://openalex.org/W2998012869","https://openalex.org/W3013640429","https://openalex.org/W3021261768","https://openalex.org/W3093588714","https://openalex.org/W3102937397","https://openalex.org/W3104947433","https://openalex.org/W3128663629","https://openalex.org/W3133280431","https://openalex.org/W6608036500","https://openalex.org/W6755207826","https://openalex.org/W6784155536"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W2349635380","https://openalex.org/W2353819554","https://openalex.org/W2359488321","https://openalex.org/W2389866386","https://openalex.org/W1516679419","https://openalex.org/W190396239"],"abstract_inverted_index":{"Perspective":[0],"ambiguity":[1,187],"widely":[2],"exists":[3],"in":[4,8,35,158,192],"human-robot":[5,193],"interaction,":[6],"especially":[7],"the":[9,18,76,106,113,117,120,123,127,140,159,165,180,185],"language-driven":[10,36],"robot":[11,37],"manipulation.":[12,38],"It":[13],"is":[14,33,72,83,102],"easy":[15],"to":[16,50,74,86,104,183],"place":[17],"object":[19,150],"at":[20],"a":[21,44,65,146],"wrong":[22],"position":[23],"just":[24],"because":[25],"of":[26,112,119],"different":[27],"perspectives.":[28],"Thus,":[29],"placement":[30,96,108,189],"location":[31,109,148],"determination":[32],"required":[34],"In":[39],"this":[40,52],"letter,":[41],"we":[42,163],"introduced":[43],"Language-Driven":[45],"Perspective-based":[46],"Pick-and-Place":[47],"Algorithm":[48],"(LD3PA)":[49],"solve":[51,184],"problem.":[53],"By":[54],"taking":[55],"natural":[56],"language":[57],"description,":[58],"image":[59],"and":[60,90,110,122,188],"point":[61],"cloud":[62],"from":[63,92],"Kinects,":[64],"perspective":[66,153,186],"disambiguation":[67,154],"network":[68,82],"using":[69],"multi-head":[70],"self-attention":[71],"proposed":[73,103,133,176],"infer":[75],"user\u2019s":[77,93,141],"perspective.":[78],"A":[79,95],"command":[80],"analysis":[81],"also":[84,144],"designed":[85],"decode":[87],"object\u2019s":[88],"role":[89],"relation":[91],"commands.":[94],"optimization":[97,190],"algorithm":[98,166],"based":[99],"on":[100,126,167],"convolution":[101],"find":[105,145],"final":[107],"orientation":[111],"picked":[114],"objects":[115,124],"considering":[116],"edge":[118],"table":[121],"already":[125],"table.":[128],"Experiments":[129],"show":[130],"that":[131,174],"our":[132,175],"LD3PA":[134,177],"could":[135,178],"not":[136],"only":[137],"correctly":[138],"disambiguate":[139],"perspective,":[142],"but":[143],"good":[147],"for":[149],"placement.":[151],"The":[152,171],"ability":[155],"outperforms":[156],"human":[157],"comparable":[160],"experiment.":[161],"Finally,":[162],"implement":[164],"physical":[168],"Panda":[169],"Robot.":[170],"result":[172],"shows":[173],"fuse":[179],"multi-modal":[181],"information":[182],"problem":[191],"interaction.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}