{"id":"https://openalex.org/W4200265593","doi":"https://doi.org/10.1109/iros51168.2021.9636362","title":"DMotion: Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos","display_name":"DMotion: Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W4200265593","doi":"https://doi.org/10.1109/iros51168.2021.9636362"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636362","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 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":"2021 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/A5071791208","display_name":"Haoqi Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoqi Yuan","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086096450","display_name":"Ruihai Wu","orcid":"https://orcid.org/0009-0008-5767-7529"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihai Wu","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102809349","display_name":"Andrew Zhao","orcid":"https://orcid.org/0000-0002-3563-0278"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Andrew Zhao","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076486783","display_name":"Haipeng Zhang","orcid":"https://orcid.org/0000-0001-5662-2106"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haipeng Zhang","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002742139","display_name":"Zihan Ding","orcid":"https://orcid.org/0009-0005-2008-4816"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zihan Ding","raw_affiliation_strings":["Princeton University"],"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100709866","display_name":"Hao Dong","orcid":"https://orcid.org/0000-0002-5101-7430"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Dong","raw_affiliation_strings":["Peking University","Peng Cheng Lab"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Lab","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5071791208"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.4363,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47685617,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"7135","last_page":"7142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9968000054359436,"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":0.9940999746322632,"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":0.8166604042053223},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6106668710708618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.586457371711731},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.537823498249054},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.47938302159309387},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45481622219085693},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.44291016459465027},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4299486577510834},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38614434003829956},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3340287208557129},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.09682461619377136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166604042053223},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6106668710708618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.586457371711731},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.537823498249054},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.47938302159309387},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45481622219085693},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.44291016459465027},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4299486577510834},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38614434003829956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3340287208557129},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.09682461619377136},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros51168.2021.9636362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636362","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 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":"2021 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/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1522301498","https://openalex.org/W1577352482","https://openalex.org/W1923344279","https://openalex.org/W1959608418","https://openalex.org/W2120606367","https://openalex.org/W2443711627","https://openalex.org/W2528489519","https://openalex.org/W2615413256","https://openalex.org/W2619034550","https://openalex.org/W2626073992","https://openalex.org/W2738136547","https://openalex.org/W2747264013","https://openalex.org/W2755486058","https://openalex.org/W2769257693","https://openalex.org/W2786615588","https://openalex.org/W2786969620","https://openalex.org/W2804010078","https://openalex.org/W2808493349","https://openalex.org/W2808707363","https://openalex.org/W2894593111","https://openalex.org/W2909331752","https://openalex.org/W2911054817","https://openalex.org/W2913229415","https://openalex.org/W2914584948","https://openalex.org/W2919112510","https://openalex.org/W2922427205","https://openalex.org/W2944892105","https://openalex.org/W2949678110","https://openalex.org/W2951158510","https://openalex.org/W2954718200","https://openalex.org/W2955368974","https://openalex.org/W2963402657","https://openalex.org/W2963547393","https://openalex.org/W2964173765","https://openalex.org/W2988603490","https://openalex.org/W2991222810","https://openalex.org/W3004116079","https://openalex.org/W3031088856","https://openalex.org/W4211147054","https://openalex.org/W4251009746","https://openalex.org/W4288088514","https://openalex.org/W4288094291","https://openalex.org/W4293376383","https://openalex.org/W4295246696","https://openalex.org/W4298157202","https://openalex.org/W4298159930","https://openalex.org/W6618372016","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6712884540","https://openalex.org/W6720244596","https://openalex.org/W6738465933","https://openalex.org/W6738467200","https://openalex.org/W6739378191","https://openalex.org/W6742720488","https://openalex.org/W6745193426","https://openalex.org/W6746530577","https://openalex.org/W6747607884","https://openalex.org/W6750253780","https://openalex.org/W6750305351","https://openalex.org/W6750642828","https://openalex.org/W6752217255","https://openalex.org/W6752365561","https://openalex.org/W6752643364","https://openalex.org/W6754539604","https://openalex.org/W6757445176","https://openalex.org/W6758420182","https://openalex.org/W6758485658","https://openalex.org/W6759669191","https://openalex.org/W6762284573","https://openalex.org/W6764769363","https://openalex.org/W6765456200","https://openalex.org/W6769281838","https://openalex.org/W6769570503","https://openalex.org/W6770507128"],"related_works":["https://openalex.org/W8302103","https://openalex.org/W2737719445","https://openalex.org/W3171631314","https://openalex.org/W2606825221","https://openalex.org/W2064245428","https://openalex.org/W2674584172","https://openalex.org/W1990892711","https://openalex.org/W2184085865","https://openalex.org/W2124621291","https://openalex.org/W4323870231"],"abstract_inverted_index":{"Learning":[0],"an":[1,74,80,107,143],"accurate":[2,108,129],"model":[3,53,66,110,139],"of":[4,62],"the":[5,60,67,99,128],"environment":[6,124],"is":[7],"essential":[8],"for":[9,146],"model-based":[10],"control":[11,18,123,141],"tasks.":[12],"Existing":[13],"methods":[14],"in":[15,35,79,111,125,138],"robotic":[16,147],"visuomotor":[17],"usually":[19],"learn":[20],"from":[21,54],"data":[22,56],"with":[23,40],"heavily":[24],"labelled":[25],"actions,":[26],"object":[27,71],"entities":[28],"or":[29],"locations,":[30],"which":[31],"can":[32],"be":[33],"demanding":[34],"many":[36],"cases.":[37],"To":[38],"cope":[39],"this":[41],"limitation,":[42],"we":[43,133],"propose":[44],"a":[45,51,112,119],"method,":[46],"dubbed":[47],"DMotion,":[48],"that":[49],"trains":[50],"forward":[52,109,131],"video":[55,150],"only,":[57],"via":[58],"disentangling":[59],"motion":[61],"controllable":[63],"agent":[64],"to":[65],"transition":[68],"dynamics.":[69],"An":[70],"extractor":[72],"and":[73,151],"interaction":[75],"learner":[76],"are":[77,88,154],"trained":[78],"end-to-end":[81],"manner":[82],"without":[83],"supervision.":[84],"The":[85],"agent\u2019s":[86],"motions":[87],"explicitly":[89],"represented":[90],"using":[91],"spatial":[92],"transformation":[93],"matrices":[94],"containing":[95],"physical":[96],"meanings.":[97],"In":[98],"experiments,":[100],"DMotion":[101],"achieves":[102],"superior":[103],"performance":[104],"on":[105],"learning":[106],"Grid":[113],"World":[114],"environment,":[115],"as":[116,118,142],"well":[117],"more":[120,152],"realistic":[121],"robot":[122],"simulation.":[126],"With":[127],"learned":[130],"models,":[132],"further":[134],"demonstrate":[135],"their":[136],"usage":[137],"predictive":[140],"effective":[144],"approach":[145],"manipulations.":[148],"Code,":[149],"materials":[153],"available":[155],"at:":[156],"https://hyperplane-lab.github.io/dmotion.":[157]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}