{"id":"https://openalex.org/W4413944816","doi":"https://doi.org/10.1109/icra55743.2025.11127521","title":"Dynamic Non-Prehensile Object Transport via Model-Predictive Reinforcement Learning","display_name":"Dynamic Non-Prehensile Object Transport via Model-Predictive Reinforcement Learning","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413944816","doi":"https://doi.org/10.1109/icra55743.2025.11127521"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5098921446","display_name":"Neel Jawale","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neel Jawale","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110797782","display_name":"Byron Boots","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byron Boots","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053446613","display_name":"Balakumar Sundaralingam","orcid":"https://orcid.org/0000-0003-3106-4755"},"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":"Balakumar Sundaralingam","raw_affiliation_strings":["NVIDIA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017774267","display_name":"Mohak Bhardwaj","orcid":"https://orcid.org/0000-0002-4775-8113"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohak Bhardwaj","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3647","last_page":"3653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6818000078201294,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6818000078201294,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.6265000104904175,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10653","display_name":"Robot Manipulation and Learning","score":0.583899974822998,"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/prehensile-tail","display_name":"Prehensile tail","score":0.9387867450714111},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8086352348327637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6351313591003418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4968266785144806},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.47521620988845825},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.06345409154891968}],"concepts":[{"id":"https://openalex.org/C136380597","wikidata":"https://www.wikidata.org/wiki/Q10508905","display_name":"Prehensile tail","level":2,"score":0.9387867450714111},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8086352348327637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6351313591003418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4968266785144806},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47521620988845825},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.06345409154891968},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2134491302","https://openalex.org/W2410617946","https://openalex.org/W2522564208","https://openalex.org/W2909331752","https://openalex.org/W3169652585","https://openalex.org/W4285102179","https://openalex.org/W4382657735","https://openalex.org/W4387623874"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2465876097","https://openalex.org/W2028231052","https://openalex.org/W2768832826","https://openalex.org/W3166169123","https://openalex.org/W2010045274","https://openalex.org/W2552641899","https://openalex.org/W2105329304"],"abstract_inverted_index":{"We":[0,29,103,155],"investigate":[1],"the":[2,18,105,120,163],"problem":[3],"of":[4,26,47,128,165,173],"teaching":[5],"a":[6,23,115,159],"robot":[7,118,121,174],"manipulator":[8],"to":[9,62,65,73,94,142,176],"perform":[10,177],"dynamic":[11],"non-prehensile":[12,178],"object":[13],"transport,":[14],"also":[15],"known":[16],"as":[17],"\u2018robot":[19],"waiter\u2019":[20],"task,":[21],"from":[22,50,83,132],"limited":[24,66],"set":[25],"real-world":[27,112],"demonstrations.":[28,136,154],"propose":[30],"an":[31,45,58],"approach":[32,70,107,139],"that":[33,157],"combines":[34],"batch":[35],"reinforcement":[36],"learning":[37,81],"(RL)":[38],"with":[39,75,87],"modelpredictive":[40],"control":[41],"(MPC)":[42],"by":[43],"pretraining":[44],"ensemble":[46],"value":[48,129],"functions":[49,130],"demonstration":[51],"data,":[52],"and":[53,79,100,111,124,149,169,183],"utilizing":[54],"them":[55],"online":[56],"within":[57],"uncertainty-aware":[59],"MPC":[60,77,93],"scheme":[61],"ensure":[63,95],"robustness":[64],"data":[67],"coverage.":[68],"Our":[69],"is":[71],"straightforward":[72],"integrate":[74],"off-the-shelf":[76],"frameworks":[78],"enables":[80,140],"solely":[82],"task":[84,123],"space":[85,98],"demonstrations":[86,168],"sparsely":[88],"labeled":[89],"transitions,":[90],"while":[91],"leveraging":[92],"smooth":[96],"joint":[97],"motions":[99],"constraint":[101],"satisfaction.":[102],"validate":[104],"proposed":[106],"through":[108],"extensive":[109,167],"simulated":[110],"experiments":[113],"on":[114],"Franka":[116],"Panda":[117],"performing":[119],"waiter":[122],"demonstrate":[125],"robust":[126],"deployment":[127],"learned":[131],"50":[133],"\u2013":[134],"100":[135],"Furthermore,":[137],"our":[138],"generalization":[141],"novel":[143],"objects":[144],"not":[145],"seen":[146],"during":[147],"training":[148,172],"can":[150,161,186],"improve":[151],"upon":[152],"suboptimal":[153],"believe":[156],"such":[158],"framework":[160],"reduce":[162],"burden":[164],"providing":[166],"facilitate":[170],"rapid":[171],"manipulators":[175],"manipulation":[179],"tasks.":[180],"Project":[181],"videos":[182],"supplementary":[184],"material":[185],"be":[187],"found":[188],"at:":[189],"https://sites.google.com/view/cvmpc":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}