{"id":"https://openalex.org/W4385660512","doi":"https://doi.org/10.1007/s40747-023-01174-5","title":"Learning high-level robotic manipulation actions with visual predictive model","display_name":"Learning high-level robotic manipulation actions with visual predictive model","publication_year":2023,"publication_date":"2023-08-08","ids":{"openalex":"https://openalex.org/W4385660512","doi":"https://doi.org/10.1007/s40747-023-01174-5"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-023-01174-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-023-01174-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01174-5.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01174-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042342752","display_name":"Anji Ma","orcid":"https://orcid.org/0000-0001-7470-0155"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anji Ma","raw_affiliation_strings":["School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006531502","display_name":"Guoyi Chi","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Guoyi Chi","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022711233","display_name":"Serena Ivaldi","orcid":"https://orcid.org/0000-0001-5349-9835"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Serena Ivaldi","raw_affiliation_strings":["Inria, University of Lorraine, CNRS, Loria, 54000, Villers-l\u00e9s-Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, University of Lorraine, CNRS, Loria, 54000, Villers-l\u00e9s-Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590","https://openalex.org/I4210121838"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005481703","display_name":"Lipeng Chen","orcid":"https://orcid.org/0000-0001-8508-6699"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Lipeng Chen","raw_affiliation_strings":["School of Computing, University of Leeds, Leeds, UK"],"raw_orcid":"https://orcid.org/0000-0001-8508-6699","affiliations":[{"raw_affiliation_string":"School of Computing, University of Leeds, Leeds, UK","institution_ids":["https://openalex.org/I130828816"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005481703"],"corresponding_institution_ids":["https://openalex.org/I130828816"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":0.2355,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51348177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"10","issue":"1","first_page":"811","last_page":"823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9994999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987999796867371,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7239952683448792},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6904681921005249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6690061092376709},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5518980622291565},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5024199485778809},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41836225986480713},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4094121754169464},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3606143891811371}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7239952683448792},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6904681921005249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6690061092376709},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5518980622291565},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5024199485778809},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41836225986480713},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4094121754169464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3606143891811371},{"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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s40747-023-01174-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-023-01174-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01174-5.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:210643","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.whiterose.ac.uk/210643/1/s40747-023-01174-5.pdf","source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:febc402743134fb3970f9a598f2de5af","is_oa":true,"landing_page_url":"https://doaj.org/article/febc402743134fb3970f9a598f2de5af","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 10, Iss 1, Pp 811-823 (2023)","raw_type":"article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/173569","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/173569","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1007/s40747-023-01174-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-023-01174-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01174-5.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385660512.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1521162839","https://openalex.org/W1930563420","https://openalex.org/W1969074599","https://openalex.org/W2039918963","https://openalex.org/W2101032778","https://openalex.org/W2114770744","https://openalex.org/W2115579991","https://openalex.org/W2133665775","https://openalex.org/W2153219011","https://openalex.org/W2528489519","https://openalex.org/W2575705757","https://openalex.org/W2593617942","https://openalex.org/W2626530627","https://openalex.org/W2747329762","https://openalex.org/W2905739540","https://openalex.org/W2962785568","https://openalex.org/W2963280855","https://openalex.org/W2963678509","https://openalex.org/W2964239605","https://openalex.org/W3099112683","https://openalex.org/W3133787995","https://openalex.org/W3164267792","https://openalex.org/W3174902251","https://openalex.org/W3207181464","https://openalex.org/W4205513846","https://openalex.org/W4243385754","https://openalex.org/W4310262435","https://openalex.org/W6602380923","https://openalex.org/W6602704705","https://openalex.org/W6603963165"],"related_works":["https://openalex.org/W2975200075","https://openalex.org/W2007544051","https://openalex.org/W1837097281","https://openalex.org/W1966410754","https://openalex.org/W2363840281","https://openalex.org/W2325242284","https://openalex.org/W2789220062","https://openalex.org/W2030539674","https://openalex.org/W2095705906","https://openalex.org/W2732308154"],"abstract_inverted_index":{"Abstract":[0],"Learning":[1],"visual":[2,103],"predictive":[3,13,104],"models":[4,14],"has":[5],"great":[6],"potential":[7],"for":[8,82],"real-world":[9,20],"robot":[10,28,43,54,83,95,141,176],"manipulations.":[11],"Visual":[12],"serve":[15],"as":[16],"a":[17,79,91,101,112,158,164,172],"model":[18,105,129,162],"of":[19,63,70,122,148,174],"dynamics":[21,135],"to":[22,116],"comprehend":[23],"the":[24,27,35,118,133,137],"interactions":[25],"between":[26],"and":[29,51,111],"objects.":[30],"However,":[31],"prior":[32],"works":[33],"in":[34,48],"literature":[36],"have":[37],"focused":[38],"mainly":[39],"on":[40,146,171],"low-level":[41,71],"elementary":[42],"actions,":[44],"which":[45],"typically":[46],"result":[47],"lengthy,":[49],"inefficient,":[50],"highly":[52],"complex":[53],"manipulation.":[55],"In":[56],"contrast,":[57],"humans":[58],"usually":[59],"employ":[60],"top\u2013down":[61],"thinking":[62],"high-level":[64,94,123,149,169],"actions":[65,170],"rather":[66],"than":[67],"bottom\u2013up":[68],"stacking":[69],"ones.":[72],"To":[73],"address":[74],"this":[75],"limitation,":[76],"we":[77],"present":[78],"novel":[80,102],"formulation":[81],"manipulation":[84,177],"that":[85,106,127],"can":[86,130],"be":[87],"accomplished":[88],"by":[89],"pick-and-place,":[90],"commonly":[92],"applied":[93],"action,":[96],"through":[97],"grasping.":[98],"We":[99,152],"propose":[100],"combines":[107],"an":[108],"action":[109],"decomposer":[110],"video":[113],"prediction":[114],"network":[115],"learn":[117],"intrinsic":[119],"semantic":[120],"information":[121],"actions.":[124,151],"Experiments":[125],"show":[126],"our":[128,161],"accurately":[131],"predict":[132],"object":[134,138],"(i.e.,":[136],"movements":[139],"under":[140],"manipulation)":[142],"while":[143],"trained":[144],"directly":[145],"observations":[147],"pick-and-place":[150],"also":[153],"demonstrate":[154],"that,":[155],"together":[156],"with":[157],"sampling-based":[159],"planner,":[160],"achieves":[163],"higher":[165],"success":[166],"rate":[167],"using":[168],"variety":[173],"real":[175],"tasks.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-25T23:04:38.658462","created_date":"2025-10-10T00:00:00"}