{"id":"https://openalex.org/W4312614111","doi":"https://doi.org/10.1109/iros47612.2022.9981832","title":"Transporters with Visual Foresight for Solving Unseen Rearrangement Tasks","display_name":"Transporters with Visual Foresight for Solving Unseen Rearrangement Tasks","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312614111","doi":"https://doi.org/10.1109/iros47612.2022.9981832"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981832","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5044013282","display_name":"Hongtao Wu","orcid":"https://orcid.org/0000-0002-6442-8159"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongtao Wu","raw_affiliation_strings":["The Johns Hopkins University,Baltimore,MD,USA,21218"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University,Baltimore,MD,USA,21218","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078529351","display_name":"Jikai Ye","orcid":"https://orcid.org/0009-0003-1173-814X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jikai Ye","raw_affiliation_strings":["National University of Singapore,Singapore","National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641794","display_name":"Xin Meng","orcid":"https://orcid.org/0000-0003-3899-1471"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xin Meng","raw_affiliation_strings":["National University of Singapore,Singapore","National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044926286","display_name":"Chris Paxton","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Paxton","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012775344","display_name":"Gregory S. Chirikjian","orcid":"https://orcid.org/0000-0003-0542-9028"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Gregory S. Chirikjian","raw_affiliation_strings":["National University of Singapore,Singapore","National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10756","last_page":"10763"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998000264167786,"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":0.9998000264167786,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.9922999739646912,"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/computer-science","display_name":"Computer science","score":0.7328028678894043},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6769909858703613},{"id":"https://openalex.org/keywords/futures-studies","display_name":"Futures studies","score":0.6470510959625244},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6239062547683716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.618377685546875},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6094424724578857},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5798881649971008},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49712803959846497},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4746730327606201},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44211190938949585},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4041932225227356},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12860187888145447},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11198481917381287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7328028678894043},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6769909858703613},{"id":"https://openalex.org/C64848388","wikidata":"https://www.wikidata.org/wiki/Q188867","display_name":"Futures studies","level":2,"score":0.6470510959625244},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6239062547683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.618377685546875},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6094424724578857},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5798881649971008},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49712803959846497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4746730327606201},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44211190938949585},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4041932225227356},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12860187888145447},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11198481917381287},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981832","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W46565623","https://openalex.org/W1903029394","https://openalex.org/W2012204020","https://openalex.org/W2068127265","https://openalex.org/W2106363968","https://openalex.org/W2194775991","https://openalex.org/W2528489519","https://openalex.org/W2601322194","https://openalex.org/W2788775653","https://openalex.org/W2963703448","https://openalex.org/W2964055695","https://openalex.org/W2968967434","https://openalex.org/W2977856604","https://openalex.org/W3008535267","https://openalex.org/W3012008866","https://openalex.org/W3013821552","https://openalex.org/W3039258510","https://openalex.org/W3101103779","https://openalex.org/W3128894241","https://openalex.org/W3133137374","https://openalex.org/W3166648240","https://openalex.org/W3173991492","https://openalex.org/W3179146632","https://openalex.org/W3200958309","https://openalex.org/W3205918749","https://openalex.org/W3207181464","https://openalex.org/W3210327237","https://openalex.org/W3210940825","https://openalex.org/W4212774754","https://openalex.org/W4239943352","https://openalex.org/W4283787240","https://openalex.org/W4287209565","https://openalex.org/W4288322145","https://openalex.org/W4298159930","https://openalex.org/W6684488266","https://openalex.org/W6713184877","https://openalex.org/W6713200026","https://openalex.org/W6735944222","https://openalex.org/W6744181227","https://openalex.org/W6745193426","https://openalex.org/W6749031613","https://openalex.org/W6764529735","https://openalex.org/W6767104088","https://openalex.org/W6768523115","https://openalex.org/W6775647304","https://openalex.org/W6785308759","https://openalex.org/W6793853427","https://openalex.org/W6801810553","https://openalex.org/W6801890467","https://openalex.org/W6803907486","https://openalex.org/W6803923185"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W3213722473"],"abstract_inverted_index":{"Rearrangement":[0],"tasks":[1,84,104,119],"have":[2],"been":[3],"identified":[4],"as":[5],"a":[6,25,43,55,75,86,97],"crucial":[7],"challenge":[8],"for":[9,17,29],"intelligent":[10],"robotic":[11],"manipulation,":[12],"but":[13],"few":[14],"methods":[15],"allow":[16],"precise":[18],"construction":[19],"of":[20,77,96,141],"unseen":[21,83,103,118],"structures.":[22],"We":[23],"propose":[24],"visual":[26],"foresight":[27],"model":[28],"pick-and-place":[30],"rearrangement":[31],"manipulation":[32],"which":[33,48],"is":[34,69,90],"able":[35,70,91],"to":[36,71,81,92,123,131],"learn":[37,72],"efficiently.":[38],"In":[39,111],"addition,":[40],"we":[41],"develop":[42],"multi-modal":[44],"action":[45],"proposal":[46],"module":[47],"builds":[49],"on":[50,102,117,149],"the":[51,94,113],"Goal-Conditioned":[52],"Transporter":[53],"Network,":[54],"state-of-the-art":[56,98],"imitation":[57,99],"learning":[58,100],"method.":[59],"Our":[60],"image-based":[61],"task":[62],"planning":[63],"method,":[64],"Transporters":[65],"with":[66],"Visual":[67],"Foresight,":[68],"from":[73,121,129],"only":[74,139],"handful":[76],"data":[78],"and":[79,107,128,145],"generalize":[80],"multiple":[82],"in":[85,105,125,133],"zero-shot":[87],"manner.":[88],"TVF":[89],"improve":[93],"performance":[95],"method":[101],"simulation":[106,126],"real":[108,134],"robot":[109,135],"experiments.":[110],"particular,":[112],"average":[114],"success":[115],"rate":[116],"improves":[120],"55.4%":[122],"78.5%":[124],"experiments":[127,136],"30%":[130],"63.3%":[132],"when":[137],"given":[138],"tens":[140],"expert":[142],"demonstrations.":[143],"Video":[144],"code":[146],"are":[147],"available":[148],"our":[150],"project":[151],"website:":[152],"https://chirikjianlab.github.io/tvf/":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}