{"id":"https://openalex.org/W4384519010","doi":"https://doi.org/10.1109/lra.2023.3295236","title":"Sim-to-Real Model-Based and Model-Free Deep Reinforcement Learning for Tactile Pushing","display_name":"Sim-to-Real Model-Based and Model-Free Deep Reinforcement Learning for Tactile Pushing","publication_year":2023,"publication_date":"2023-07-17","ids":{"openalex":"https://openalex.org/W4384519010","doi":"https://doi.org/10.1109/lra.2023.3295236"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3295236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3295236","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research-information.bris.ac.uk/en/publications/35825b50-76cc-48ed-bd80-0c1bb90b1f6d","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018901243","display_name":"Max Yang","orcid":"https://orcid.org/0000-0002-3643-0585"},"institutions":[{"id":"https://openalex.org/I4210161128","display_name":"Bristol Robotics Laboratory","ror":"https://ror.org/056sbyc67","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210161128"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Max Yang","raw_affiliation_strings":["Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K","institution_ids":["https://openalex.org/I4210161128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044755774","display_name":"Yijiong Lin","orcid":"https://orcid.org/0000-0002-0063-0905"},"institutions":[{"id":"https://openalex.org/I4210161128","display_name":"Bristol Robotics Laboratory","ror":"https://ror.org/056sbyc67","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210161128"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yijiong Lin","raw_affiliation_strings":["Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K","institution_ids":["https://openalex.org/I4210161128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053354197","display_name":"Alex Church","orcid":"https://orcid.org/0000-0002-4062-5959"},"institutions":[{"id":"https://openalex.org/I4210161128","display_name":"Bristol Robotics Laboratory","ror":"https://ror.org/056sbyc67","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210161128"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alex Church","raw_affiliation_strings":["Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K","institution_ids":["https://openalex.org/I4210161128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025972235","display_name":"John W. Lloyd","orcid":"https://orcid.org/0000-0002-5630-683X"},"institutions":[{"id":"https://openalex.org/I4210161128","display_name":"Bristol Robotics Laboratory","ror":"https://ror.org/056sbyc67","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210161128"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John Lloyd","raw_affiliation_strings":["Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K","institution_ids":["https://openalex.org/I4210161128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386760","display_name":"Dandan Zhang","orcid":"https://orcid.org/0000-0001-7649-7605"},"institutions":[{"id":"https://openalex.org/I4210161128","display_name":"Bristol Robotics Laboratory","ror":"https://ror.org/056sbyc67","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210161128"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dandan Zhang","raw_affiliation_strings":["Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K","institution_ids":["https://openalex.org/I4210161128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037188932","display_name":"David A. W. Barton","orcid":"https://orcid.org/0000-0002-0595-4239"},"institutions":[{"id":"https://openalex.org/I4210161128","display_name":"Bristol Robotics Laboratory","ror":"https://ror.org/056sbyc67","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210161128"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David A.W. Barton","raw_affiliation_strings":["Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K","institution_ids":["https://openalex.org/I4210161128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015897265","display_name":"Nathan F. Lepora","orcid":"https://orcid.org/0000-0001-5327-1523"},"institutions":[{"id":"https://openalex.org/I4210161128","display_name":"Bristol Robotics Laboratory","ror":"https://ror.org/056sbyc67","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210161128"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nathan F. Lepora","raw_affiliation_strings":["Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K","institution_ids":["https://openalex.org/I4210161128"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5018901243"],"corresponding_institution_ids":["https://openalex.org/I4210161128"],"apc_list":null,"apc_paid":null,"fwci":3.1087,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91807776,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"8","issue":"9","first_page":"5480","last_page":"5487"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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":0.9994000196456909,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10338","display_name":"Advanced Sensor and Energy Harvesting Materials","score":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8495333194732666},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.715867280960083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6712414026260376},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6329885125160217},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5174949169158936},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.49741438031196594},{"id":"https://openalex.org/keywords/simplicity","display_name":"Simplicity","score":0.44729453325271606},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3464828133583069},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34269654750823975},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34012722969055176}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8495333194732666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715867280960083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6712414026260376},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6329885125160217},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5174949169158936},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.49741438031196594},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.44729453325271606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3464828133583069},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34269654750823975},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34012722969055176},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/lra.2023.3295236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3295236","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:research-information.bris.ac.uk:openaire/35825b50-76cc-48ed-bd80-0c1bb90b1f6d","is_oa":true,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/35825b50-76cc-48ed-bd80-0c1bb90b1f6d","pdf_url":null,"source":{"id":"https://openalex.org/S7407055359","display_name":"Explore Bristol Research","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Yang, M, Lin, Y, Church, A D J R, Lloyd, J A, Zhang, D, Barton, D A W & Lepora, N F 2023, 'Sim-to-Real Model-Based and Model-Free Deep Reinforcement Learning for Tactile Pushing', IEEE Robotics and Automation Letters, vol. 8, no. 9, pp. 5480 - 5487. https://doi.org/10.1109/LRA.2023.3295236","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:2307.14272","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.14272","pdf_url":"https://arxiv.org/pdf/2307.14272","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"","raw_type":"text"},{"id":"pmh:oai:research-information.bris.ac.uk:publications/35825b50-76cc-48ed-bd80-0c1bb90b1f6d","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85164802850&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:research-information.bris.ac.uk:openaire/35825b50-76cc-48ed-bd80-0c1bb90b1f6d","is_oa":true,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/35825b50-76cc-48ed-bd80-0c1bb90b1f6d","pdf_url":null,"source":{"id":"https://openalex.org/S7407055359","display_name":"Explore Bristol Research","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Yang, M, Lin, Y, Church, A D J R, Lloyd, J A, Zhang, D, Barton, D A W & Lepora, N F 2023, 'Sim-to-Real Model-Based and Model-Free Deep Reinforcement Learning for Tactile Pushing', IEEE Robotics and Automation Letters, vol. 8, no. 9, pp. 5480 - 5487. https://doi.org/10.1109/LRA.2023.3295236","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7896653347","display_name":null,"funder_award_id":"RL-2016-39","funder_id":"https://openalex.org/F4320319993","funder_display_name":"Leverhulme Trust"}],"funders":[{"id":"https://openalex.org/F4320319993","display_name":"Leverhulme Trust","ror":"https://ror.org/012mzw131"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1594201624","https://openalex.org/W1806263934","https://openalex.org/W2050708324","https://openalex.org/W2099951169","https://openalex.org/W2763994565","https://openalex.org/W2781493652","https://openalex.org/W2781726626","https://openalex.org/W2823112946","https://openalex.org/W2883172488","https://openalex.org/W2885596080","https://openalex.org/W2895710106","https://openalex.org/W2902125520","https://openalex.org/W2962793652","https://openalex.org/W2963030226","https://openalex.org/W3004357679","https://openalex.org/W3015462157","https://openalex.org/W3032792332","https://openalex.org/W3086412568","https://openalex.org/W3086512743","https://openalex.org/W3091760204","https://openalex.org/W3106087774","https://openalex.org/W3112669067","https://openalex.org/W3128582681","https://openalex.org/W3130076912","https://openalex.org/W3155729845","https://openalex.org/W3198417399","https://openalex.org/W3198507954","https://openalex.org/W3205950068","https://openalex.org/W3208675475","https://openalex.org/W3216772467","https://openalex.org/W4214902667","https://openalex.org/W4285232917","https://openalex.org/W4287118130","https://openalex.org/W4288029271","https://openalex.org/W4292231110","https://openalex.org/W4293872189","https://openalex.org/W4298206671","https://openalex.org/W6635701881","https://openalex.org/W6638365565","https://openalex.org/W6747473740","https://openalex.org/W6748599296","https://openalex.org/W6751494529","https://openalex.org/W6753046885","https://openalex.org/W6753060773","https://openalex.org/W6756908582","https://openalex.org/W6767226293","https://openalex.org/W6783068448","https://openalex.org/W6794067299","https://openalex.org/W6802188089","https://openalex.org/W6802749953","https://openalex.org/W6804601995"],"related_works":["https://openalex.org/W2368019753","https://openalex.org/W2333930193","https://openalex.org/W2737356002","https://openalex.org/W2246241526","https://openalex.org/W2374150061","https://openalex.org/W4301122218","https://openalex.org/W2081340182","https://openalex.org/W2369703001","https://openalex.org/W2372323577","https://openalex.org/W2321432690"],"abstract_inverted_index":{"Object":[0],"pushing":[1,55,82,132,145,168],"presents":[2],"a":[3,31,49,67,86,94,107,111,126,155,160],"key":[4],"non-prehensile":[5],"manipulation":[6,15],"problem":[7],"that":[8,70,100,122,149],"is":[9,102],"illustrative":[10],"of":[11,33,114,128,175,186],"more":[12,152,166],"complex":[13],"robotic":[14],"tasks.":[16],"While":[17],"deep":[18,50],"reinforcement":[19],"learning":[20,26],"(RL)":[21],"methods":[22],"have":[23],"demonstrated":[24],"impressive":[25],"capabilities":[27],"using":[28,56],"visual":[29,60],"input,":[30,61],"lack":[32],"tactile":[34,57,63,188],"sensing":[35,58],"limits":[36],"their":[37],"capability":[38],"for":[39,81,190],"fine":[40,191],"and":[41,74,110,119,131,147,165,179],"reliable":[42,120,167],"control":[43],"during":[44],"manipulation.":[45,192],"Here":[46],"we":[47,92],"propose":[48],"RL":[51,76],"approach":[52],"to":[53,77,85,104,116,125],"object":[54,84,109],"without":[59,134],"namely":[62],"pushing.":[64],"We":[65,137],"present":[66],"goal-conditioned":[68],"formulation":[69],"allows":[71],"both":[72],"model-free":[73,156],"model-based":[75,161],"obtain":[78],"accurate":[79],"policies":[80,121],"an":[83],"goal.":[87],"To":[88],"achieve":[89],"real-world":[90,181],"performance,":[91],"adopt":[93],"sim-to-real":[95],"approach.":[96],"Our":[97],"results":[98],"demonstrate":[99],"it":[101],"possible":[103],"train":[105],"on":[106],"single":[108],"limited":[112],"sample":[113],"goals":[115],"produce":[117],"precise":[118],"can":[123,158],"generalize":[124],"variety":[127],"unseen":[129],"objects":[130],"scenarios":[133],"domain":[135],"randomization.":[136],"experiment":[138],"with":[139,150],"the":[140,184],"trained":[141],"agents":[142],"in":[143],"harsh":[144],"conditions,":[146],"show":[148],"significantly":[151],"training":[153,177],"samples,":[154],"policy":[157],"outperform":[159],"planner,":[162],"generating":[163],"shorter":[164],"trajectories":[169],"despite":[170],"large":[171],"disturbances.":[172],"The":[173],"simplicity":[174],"our":[176],"environment":[178],"effective":[180],"performance":[182],"highlights":[183],"value":[185],"rich":[187],"information":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2023-07-28T00:00:00"}