{"id":"https://openalex.org/W3205111278","doi":"https://doi.org/10.1109/icra48506.2021.9561030","title":"Multi-Step Recurrent Q-Learning for Robotic Velcro Peeling","display_name":"Multi-Step Recurrent Q-Learning for Robotic Velcro Peeling","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3205111278","doi":"https://doi.org/10.1109/icra48506.2021.9561030","mag":"3205111278"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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/A5085052085","display_name":"Jiacheng Yuan","orcid":"https://orcid.org/0000-0002-2762-242X"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiacheng Yuan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046044122","display_name":"Nicolai H\u00e4ni","orcid":"https://orcid.org/0000-0003-4042-3318"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicolai Hani","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033839227","display_name":"Volkan Isler","orcid":"https://orcid.org/0000-0002-0868-5441"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Volkan Isler","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085052085"],"corresponding_institution_ids":["https://openalex.org/I130238516"],"apc_list":null,"apc_paid":null,"fwci":0.2747,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.55188522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6657","last_page":"6663"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":1.0,"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":1.0,"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/T10868","display_name":"Soft Robotics and Applications","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.9876000285148621,"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/robot","display_name":"Robot","score":0.7715923190116882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7438358068466187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6625983715057373},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6528624296188354},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5776088833808899},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.5588986277580261},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5399119853973389},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42711737751960754},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.421736478805542},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32555341720581055},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17068949341773987},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12158730626106262}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7715923190116882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7438358068466187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6625983715057373},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6528624296188354},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5776088833808899},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.5588986277580261},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5399119853973389},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42711737751960754},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.421736478805542},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32555341720581055},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17068949341773987},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12158730626106262},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9561030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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":47,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1966487689","https://openalex.org/W1978580730","https://openalex.org/W1983156320","https://openalex.org/W1988207416","https://openalex.org/W2017801178","https://openalex.org/W2045448547","https://openalex.org/W2094808257","https://openalex.org/W2120429435","https://openalex.org/W2121092017","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2146662771","https://openalex.org/W2166459342","https://openalex.org/W2172377671","https://openalex.org/W2201912979","https://openalex.org/W2287992105","https://openalex.org/W2322971354","https://openalex.org/W2787938642","https://openalex.org/W2795550549","https://openalex.org/W2808405904","https://openalex.org/W2900130725","https://openalex.org/W2952866402","https://openalex.org/W2962679776","https://openalex.org/W2962736495","https://openalex.org/W2962793652","https://openalex.org/W2962938178","https://openalex.org/W2963033241","https://openalex.org/W2963280659","https://openalex.org/W2963504951","https://openalex.org/W2963864421","https://openalex.org/W2963923407","https://openalex.org/W2968095426","https://openalex.org/W2979717831","https://openalex.org/W2990032740","https://openalex.org/W2990747716","https://openalex.org/W3006936931","https://openalex.org/W3040477237","https://openalex.org/W3106023961","https://openalex.org/W4297686387","https://openalex.org/W6677939520","https://openalex.org/W6684921986","https://openalex.org/W6685737212","https://openalex.org/W6748839928","https://openalex.org/W6752818329","https://openalex.org/W6769506474"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W4224231624","https://openalex.org/W2332512904","https://openalex.org/W2319626700"],"abstract_inverted_index":{"Learning":[0],"object":[1],"manipulation":[2,23,48,62],"is":[3],"a":[4,43,57,81,90,143],"critical":[5],"skill":[6],"for":[7,33,46],"robots":[8],"to":[9,93,122],"interact":[10],"with":[11,28,80,130],"their":[12],"environment.":[13],"Even":[14],"though":[15],"there":[16],"has":[17],"been":[18],"significant":[19],"progress":[20],"in":[21,52,69,107,127,133],"robotic":[22,47],"of":[24,49,59,97,136],"rigid":[25],"objects,":[26],"interacting":[27],"non-rigid":[29,50],"objects":[30,51],"remains":[31],"challenging":[32],"robots.":[34],"In":[35],"this":[36],"work,":[37],"we":[38],"introduce":[39],"velcro":[40],"peeling":[41],"as":[42],"new":[44],"application":[45],"complex":[53],"environments.":[54],"We":[55,86],"present":[56,87,126],"method":[58],"learning":[60],"force-based":[61],"from":[63],"noisy":[64],"and":[65,103,109],"incomplete":[66],"sensor":[67],"inputs":[68],"partially":[70],"observable":[71],"environments":[72],"by":[73,142],"modeling":[74,98],"long":[75,100],"term":[76,101],"dependencies":[77,102],"between":[78],"measurements":[79],"multi-step":[82],"deep":[83],"recurrent":[84],"network.":[85],"experiments":[88],"on":[89],"real":[91],"robot":[92,110,121],"show":[94,114],"the":[95,120,128,140],"necessity":[96],"these":[99],"validate":[104],"our":[105],"approach":[106],"simulation":[108],"experiments.":[111],"Our":[112],"results":[113],"that":[115],"using":[116],"tactile":[117],"input":[118],"enables":[119],"overcome":[123],"geometric":[124],"uncertainties":[125],"environment":[129],"high":[131],"fidelity":[132],"\u223c":[134],"90%":[135],"all":[137],"cases,":[138],"outperforming":[139],"baselines":[141],"large":[144],"margin.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}