{"id":"https://openalex.org/W4413953937","doi":"https://doi.org/10.1177/09596518251350353","title":"Towards cost-effective and safe contact-rich robotic manipulation with reinforcement learning: A review of techniques for future industrial automation","display_name":"Towards cost-effective and safe contact-rich robotic manipulation with reinforcement learning: A review of techniques for future industrial automation","publication_year":2025,"publication_date":"2025-09-03","ids":{"openalex":"https://openalex.org/W4413953937","doi":"https://doi.org/10.1177/09596518251350353"},"language":"en","primary_location":{"id":"doi:10.1177/09596518251350353","is_oa":true,"landing_page_url":"https://doi.org/10.1177/09596518251350353","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/09596518251350353","source":{"id":"https://openalex.org/S4210196624","display_name":"Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering","issn_l":"0959-6518","issn":["0959-6518","2041-3041"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering","raw_type":"journal-article"},"type":"review","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://journals.sagepub.com/doi/pdf/10.1177/09596518251350353","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119527455","display_name":"Anselmo Parnada","orcid":"https://orcid.org/0009-0003-9385-5592"},"institutions":[{"id":"https://openalex.org/I12870472","display_name":"Birmingham City University","ror":"https://ror.org/00t67pt25","country_code":"GB","type":"education","lineage":["https://openalex.org/I12870472"]},{"id":"https://openalex.org/I4210123551","display_name":"West Midlands Police","ror":"https://ror.org/02ptdcx04","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210123551"]},{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Anselmo Parnada","raw_affiliation_strings":["School of Engineering, University of Birmingham, Birmingham, West Midlands, UK"],"raw_orcid":"https://orcid.org/0009-0003-9385-5592","affiliations":[{"raw_affiliation_string":"School of Engineering, University of Birmingham, Birmingham, West Midlands, UK","institution_ids":["https://openalex.org/I79619799","https://openalex.org/I12870472","https://openalex.org/I4210123551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070239668","display_name":"Mo Qu","orcid":"https://orcid.org/0000-0002-2333-4412"},"institutions":[{"id":"https://openalex.org/I12870472","display_name":"Birmingham City University","ror":"https://ror.org/00t67pt25","country_code":"GB","type":"education","lineage":["https://openalex.org/I12870472"]},{"id":"https://openalex.org/I4210123551","display_name":"West Midlands Police","ror":"https://ror.org/02ptdcx04","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210123551"]},{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mo Qu","raw_affiliation_strings":["School of Engineering, University of Birmingham, Birmingham, West Midlands, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, University of Birmingham, Birmingham, West Midlands, UK","institution_ids":["https://openalex.org/I79619799","https://openalex.org/I12870472","https://openalex.org/I4210123551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079759495","display_name":"Marco Castellani","orcid":"https://orcid.org/0000-0002-5623-7491"},"institutions":[{"id":"https://openalex.org/I12870472","display_name":"Birmingham City University","ror":"https://ror.org/00t67pt25","country_code":"GB","type":"education","lineage":["https://openalex.org/I12870472"]},{"id":"https://openalex.org/I4210123551","display_name":"West Midlands Police","ror":"https://ror.org/02ptdcx04","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210123551"]},{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marco Castellani","raw_affiliation_strings":["School of Engineering, University of Birmingham, Birmingham, West Midlands, UK"],"raw_orcid":"https://orcid.org/0000-0002-5623-7491","affiliations":[{"raw_affiliation_string":"School of Engineering, University of Birmingham, Birmingham, West Midlands, UK","institution_ids":["https://openalex.org/I79619799","https://openalex.org/I12870472","https://openalex.org/I4210123551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004895698","display_name":"Hyung Jin Chang","orcid":"https://orcid.org/0000-0001-7495-9677"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hyung Jin Chang","raw_affiliation_strings":["School of Computer Science, University of Birmingham, Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Birmingham, Birmingham, UK","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058814232","display_name":"Yongjing Wang","orcid":"https://orcid.org/0000-0002-9640-0871"},"institutions":[{"id":"https://openalex.org/I12870472","display_name":"Birmingham City University","ror":"https://ror.org/00t67pt25","country_code":"GB","type":"education","lineage":["https://openalex.org/I12870472"]},{"id":"https://openalex.org/I4210123551","display_name":"West Midlands Police","ror":"https://ror.org/02ptdcx04","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210123551"]},{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yongjing Wang","raw_affiliation_strings":["School of Engineering, University of Birmingham, Birmingham, West Midlands, UK"],"raw_orcid":"https://orcid.org/0000-0002-9640-0871","affiliations":[{"raw_affiliation_string":"School of Engineering, University of Birmingham, Birmingham, West Midlands, UK","institution_ids":["https://openalex.org/I79619799","https://openalex.org/I12870472","https://openalex.org/I4210123551"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5119527455"],"corresponding_institution_ids":["https://openalex.org/I12870472","https://openalex.org/I4210123551","https://openalex.org/I79619799"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27128536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"240","issue":"1","first_page":"3","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9890999794006348,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9843000173568726,"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/automation","display_name":"Automation","score":0.7478185296058655},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.724843442440033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4735129177570343},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.45863211154937744},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44215846061706543},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.38831353187561035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3628104627132416},{"id":"https://openalex.org/keywords/mechanical-engineering","display_name":"Mechanical engineering","score":0.13328394293785095}],"concepts":[{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.7478185296058655},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.724843442440033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4735129177570343},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.45863211154937744},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44215846061706543},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.38831353187561035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3628104627132416},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.13328394293785095},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/09596518251350353","is_oa":true,"landing_page_url":"https://doi.org/10.1177/09596518251350353","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/09596518251350353","source":{"id":"https://openalex.org/S4210196624","display_name":"Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering","issn_l":"0959-6518","issn":["0959-6518","2041-3041"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/07eedb67-9829-42de-8012-06d86d7e20a0","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/07eedb67-9829-42de-8012-06d86d7e20a0","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Parnada, A, Qu, M, Castellani, M, Jin Chang, H & Wang, Y 2025, 'Towards cost-effective and safe contact-rich robotic manipulation with reinforcement learning : A review of techniques for future industrial automation', Proceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering. https://doi.org/10.1177/09596518251350353","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1177/09596518251350353","is_oa":true,"landing_page_url":"https://doi.org/10.1177/09596518251350353","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/09596518251350353","source":{"id":"https://openalex.org/S4210196624","display_name":"Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering","issn_l":"0959-6518","issn":["0959-6518","2041-3041"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7660105131","display_name":"Self-learning robotics for industrial contact-rich tasks (ATARI): enabling smart learning in automated disassembly","funder_award_id":"EP/W00206X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413953937.pdf"},"referenced_works_count":141,"referenced_works":["https://openalex.org/W601228132","https://openalex.org/W1977655452","https://openalex.org/W1983497631","https://openalex.org/W1986614398","https://openalex.org/W1997543377","https://openalex.org/W2003307570","https://openalex.org/W2010561502","https://openalex.org/W2034052310","https://openalex.org/W2034965730","https://openalex.org/W2076337359","https://openalex.org/W2093575436","https://openalex.org/W2112474089","https://openalex.org/W2123651102","https://openalex.org/W2126909264","https://openalex.org/W2133932631","https://openalex.org/W2136719407","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2162218551","https://openalex.org/W2166211466","https://openalex.org/W2205490832","https://openalex.org/W2288565641","https://openalex.org/W2534225927","https://openalex.org/W2588423609","https://openalex.org/W2589515277","https://openalex.org/W2604213426","https://openalex.org/W2604382266","https://openalex.org/W2605102758","https://openalex.org/W2613619376","https://openalex.org/W2766373678","https://openalex.org/W2771354076","https://openalex.org/W2787666871","https://openalex.org/W2789839425","https://openalex.org/W2790924949","https://openalex.org/W2792919371","https://openalex.org/W2806263811","https://openalex.org/W2890218953","https://openalex.org/W2902907165","https://openalex.org/W2939569248","https://openalex.org/W2950069298","https://openalex.org/W2959488596","https://openalex.org/W3004058922","https://openalex.org/W3028308378","https://openalex.org/W3033119093","https://openalex.org/W3035756007","https://openalex.org/W3036167779","https://openalex.org/W3038822267","https://openalex.org/W3081200565","https://openalex.org/W3081877091","https://openalex.org/W3088158297","https://openalex.org/W3093426589","https://openalex.org/W3096831136","https://openalex.org/W3100172161","https://openalex.org/W3100789280","https://openalex.org/W3101875589","https://openalex.org/W3109467707","https://openalex.org/W3121342653","https://openalex.org/W3122928565","https://openalex.org/W3123742938","https://openalex.org/W3127352841","https://openalex.org/W3130500701","https://openalex.org/W3130984490","https://openalex.org/W3131959844","https://openalex.org/W3135939397","https://openalex.org/W3150718622","https://openalex.org/W3163842339","https://openalex.org/W3164862896","https://openalex.org/W3168892396","https://openalex.org/W3194103514","https://openalex.org/W3197400104","https://openalex.org/W3199096322","https://openalex.org/W3201276701","https://openalex.org/W3205950068","https://openalex.org/W3208624098","https://openalex.org/W3209627429","https://openalex.org/W3209952908","https://openalex.org/W3212386989","https://openalex.org/W4205788769","https://openalex.org/W4205837126","https://openalex.org/W4205999401","https://openalex.org/W4210489512","https://openalex.org/W4210630242","https://openalex.org/W4210700398","https://openalex.org/W4212774754","https://openalex.org/W4212996499","https://openalex.org/W4214717370","https://openalex.org/W4220832216","https://openalex.org/W4230831029","https://openalex.org/W4236957551","https://openalex.org/W4237591687","https://openalex.org/W4244264101","https://openalex.org/W4246068809","https://openalex.org/W4252315992","https://openalex.org/W4285066157","https://openalex.org/W4285225245","https://openalex.org/W4285791333","https://openalex.org/W4288885957","https://openalex.org/W4297964528","https://openalex.org/W4299345493","https://openalex.org/W4309311597","https://openalex.org/W4311057649","https://openalex.org/W4311326360","https://openalex.org/W4312771252","https://openalex.org/W4313442619","https://openalex.org/W4316876974","https://openalex.org/W4317542939","https://openalex.org/W4319302764","https://openalex.org/W4319923063","https://openalex.org/W4360898385","https://openalex.org/W4365800072","https://openalex.org/W4379527413","https://openalex.org/W4384519010","https://openalex.org/W4385245566","https://openalex.org/W4385430467","https://openalex.org/W4385757466","https://openalex.org/W4386090379","https://openalex.org/W4386750828","https://openalex.org/W4386758039","https://openalex.org/W4387092832","https://openalex.org/W4388923986","https://openalex.org/W4389637871","https://openalex.org/W4390776907","https://openalex.org/W4391921015","https://openalex.org/W4392173735","https://openalex.org/W4399330323","https://openalex.org/W4399526652","https://openalex.org/W4400905325","https://openalex.org/W4401413712","https://openalex.org/W4401415072","https://openalex.org/W4404082195","https://openalex.org/W4404198934","https://openalex.org/W4404238924","https://openalex.org/W4404733422","https://openalex.org/W4405785109","https://openalex.org/W4406815170","https://openalex.org/W4407404372","https://openalex.org/W4408100264","https://openalex.org/W4408164238","https://openalex.org/W4408166072","https://openalex.org/W4408223449","https://openalex.org/W4413344357"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2389214306","https://openalex.org/W2024136090","https://openalex.org/W2992534160","https://openalex.org/W1595058678","https://openalex.org/W3022812046"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"has":[3,58,95],"been":[4,96],"considered":[5],"a":[6],"promising":[7],"method":[8],"to":[9,29,42,50,61,71,83,109],"enable":[10],"the":[11,59,141,183],"automation":[12,202],"of":[13,145],"contact-rich":[14,47,117,149,196],"manipulation":[15,198],"tasks,":[16,150,165],"which":[17],"can":[18,154],"increase":[19],"capabilities":[20],"for":[21,46,79,114,148,179,185,195],"industrial":[22,201],"automation.":[23],"RL":[24,75,115],"facilitates":[25],"autonomous":[26],"agents\u2019":[27],"learning":[28],"solve":[30],"environments":[31],"with":[32,35],"complex":[33],"dynamics":[34],"little":[36],"human":[37],"intervention,":[38],"making":[39],"it":[40],"easier":[41],"implement":[43],"control":[44,52,57,147,194],"strategies":[45],"tasks":[48],"compared":[49,70],"traditional":[51],"approaches.":[53],"Further,":[54],"RL-based":[55,146,193],"robotic":[56,118,197],"potential":[60],"transfer":[62,163,169],"policies":[63],"between":[64,164],"task":[65],"variations,":[66],"significantly":[67,139],"improving":[68,161,166],"scalability":[69],"existing":[72],"methods.":[73],"However,":[74],"is":[76],"currently":[77],"inviable":[78],"wider":[80],"adoption":[81],"due":[82],"its":[84],"relatively":[85],"high":[86],"implementation":[87],"costs":[88],"and":[89,112,126,143,170,173,191],"safety":[90,113,144],"issues,":[91],"so":[92],"current":[93,135],"research":[94,136,159,181],"focused":[97],"on":[98],"addressing":[99],"these":[100],"issues.":[101],"This":[102],"paper":[103],"comprehensively":[104],"reviewed":[105],"recently":[106],"developed":[107],"techniques":[108],"improve":[110],"cost":[111,142],"in":[116,188,199],"manipulation.":[119],"Techniques":[120],"were":[121],"organized":[122],"by":[123,157],"their":[124,127],"approach,":[125],"impact":[128],"was":[129,132],"analysed.":[130],"It":[131],"found":[133],"that":[134],"efforts":[137],"have":[138],"improved":[140],"but":[151],"further":[152,180],"improvements":[153],"be":[155],"made":[156],"progressing":[158],"towards":[160],"knowledge":[162],"inter-robot":[167],"policy":[168],"facilitating":[171],"real-world":[172],"continual":[174],"RL.":[175],"The":[176],"identified":[177],"directions":[178],"set":[182],"stage":[184],"future":[186,200],"developments":[187],"more":[189],"versatile":[190],"cost-effective":[192],"applications.":[203]},"counts_by_year":[],"updated_date":"2026-01-10T23:39:48.068659","created_date":"2025-10-10T00:00:00"}