{"id":"https://openalex.org/W4399330323","doi":"https://doi.org/10.1007/s10514-024-10164-6","title":"Guiding real-world reinforcement learning for in-contact manipulation tasks with Shared Control Templates","display_name":"Guiding real-world reinforcement learning for in-contact manipulation tasks with Shared Control Templates","publication_year":2024,"publication_date":"2024-06-04","ids":{"openalex":"https://openalex.org/W4399330323","doi":"https://doi.org/10.1007/s10514-024-10164-6"},"language":"en","primary_location":{"id":"doi:10.1007/s10514-024-10164-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10514-024-10164-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10514-024-10164-6.pdf","source":{"id":"https://openalex.org/S144091109","display_name":"Autonomous Robots","issn_l":"0929-5593","issn":["0929-5593","1573-7527"],"is_oa":false,"is_in_doaj":false,"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":"Autonomous Robots","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10514-024-10164-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016248595","display_name":"Abhishek Padalkar","orcid":null},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Abhishek Padalkar","raw_affiliation_strings":["Robotics and Mechatronics Center (RMC), German Aerospace Center (DLR), M\u00fcnchener Str. 20, 82234, We\u00dfling, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and Mechatronics Center (RMC), German Aerospace Center (DLR), M\u00fcnchener Str. 20, 82234, We\u00dfling, Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055668072","display_name":"Gabriel Quere","orcid":"https://orcid.org/0000-0002-1788-3685"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gabriel Quere","raw_affiliation_strings":["Robotics and Mechatronics Center (RMC), German Aerospace Center (DLR), M\u00fcnchener Str. 20, 82234, We\u00dfling, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and Mechatronics Center (RMC), German Aerospace Center (DLR), M\u00fcnchener Str. 20, 82234, We\u00dfling, Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013236820","display_name":"Antonin Raffin","orcid":"https://orcid.org/0000-0001-6036-6950"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Antonin Raffin","raw_affiliation_strings":["Robotics and Mechatronics Center (RMC), German Aerospace Center (DLR), M\u00fcnchener Str. 20, 82234, We\u00dfling, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and Mechatronics Center (RMC), German Aerospace Center (DLR), M\u00fcnchener Str. 20, 82234, We\u00dfling, Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012562539","display_name":"Jo\u00e3o Silv\u00e9rio","orcid":"https://orcid.org/0000-0003-1428-8933"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Silv\u00e9rio","raw_affiliation_strings":["Robotics and Mechatronics Center (RMC), German Aerospace Center (DLR), M\u00fcnchener Str. 20, 82234, We\u00dfling, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and Mechatronics Center (RMC), German Aerospace Center (DLR), M\u00fcnchener Str. 20, 82234, We\u00dfling, Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017689065","display_name":"Freek Stulp","orcid":"https://orcid.org/0000-0001-9555-9517"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Freek Stulp","raw_affiliation_strings":["Robotics and Mechatronics Center (RMC), German Aerospace Center (DLR), M\u00fcnchener Str. 20, 82234, We\u00dfling, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and Mechatronics Center (RMC), German Aerospace Center (DLR), M\u00fcnchener Str. 20, 82234, We\u00dfling, Germany","institution_ids":["https://openalex.org/I2898391981"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016248595"],"corresponding_institution_ids":["https://openalex.org/I2898391981"],"apc_list":{"value":2590,"currency":"EUR","value_usd":3390},"apc_paid":{"value":2590,"currency":"EUR","value_usd":3390},"fwci":0.8696,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72638711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"48","issue":"4-5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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":0.9998999834060669,"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/T11687","display_name":"Teleoperation and Haptic Systems","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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":0.9947999715805054,"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/computer-science","display_name":"Computer science","score":0.9175558090209961},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8231625556945801},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.7488910555839539},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5316199660301208},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5092662572860718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4308672547340393},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1814662218093872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9175558090209961},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8231625556945801},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.7488910555839539},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5316199660301208},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5092662572860718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4308672547340393},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1814662218093872}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10514-024-10164-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10514-024-10164-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10514-024-10164-6.pdf","source":{"id":"https://openalex.org/S144091109","display_name":"Autonomous Robots","issn_l":"0929-5593","issn":["0929-5593","1573-7527"],"is_oa":false,"is_in_doaj":false,"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":"Autonomous Robots","raw_type":"journal-article"},{"id":"pmh:oai:elib.dlr.de:206235","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10514-024-10164-6>.","pdf_url":"https://elib.dlr.de/206235/1/s10514-024-10164-6.pdf","source":{"id":"https://openalex.org/S4377196266","display_name":"elib (German Aerospace Center)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2898391981","host_organization_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","host_organization_lineage":["https://openalex.org/I2898391981"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.1007/s10514-024-10164-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10514-024-10164-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10514-024-10164-6.pdf","source":{"id":"https://openalex.org/S144091109","display_name":"Autonomous Robots","issn_l":"0929-5593","issn":["0929-5593","1573-7527"],"is_oa":false,"is_in_doaj":false,"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":"Autonomous Robots","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G138487048","display_name":null,"funder_award_id":"101136067","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G1612758553","display_name":null,"funder_award_id":"101070596","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G923131758","display_name":null,"funder_award_id":"329551904","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320324729","display_name":"Universit\u00e4t Bremen","ror":"https://ror.org/04ers2y35"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399330323.pdf"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W1539716820","https://openalex.org/W1556824961","https://openalex.org/W1577216924","https://openalex.org/W1777239053","https://openalex.org/W1972894079","https://openalex.org/W1993897290","https://openalex.org/W2016773334","https://openalex.org/W2021004298","https://openalex.org/W2088038240","https://openalex.org/W2089145243","https://openalex.org/W2100235553","https://openalex.org/W2105660272","https://openalex.org/W2105925198","https://openalex.org/W2109910161","https://openalex.org/W2133932631","https://openalex.org/W2151992157","https://openalex.org/W2257979135","https://openalex.org/W2327881649","https://openalex.org/W2559960928","https://openalex.org/W2766447205","https://openalex.org/W2775192669","https://openalex.org/W2781726626","https://openalex.org/W2883140436","https://openalex.org/W2883750587","https://openalex.org/W2903420114","https://openalex.org/W2912541403","https://openalex.org/W2914688076","https://openalex.org/W2962736495","https://openalex.org/W2964319110","https://openalex.org/W2966735560","https://openalex.org/W2967355195","https://openalex.org/W2968268581","https://openalex.org/W2990747716","https://openalex.org/W2996196387","https://openalex.org/W3021619395","https://openalex.org/W3028308378","https://openalex.org/W3034808834","https://openalex.org/W3037164854","https://openalex.org/W3042273483","https://openalex.org/W3091182126","https://openalex.org/W3091552533","https://openalex.org/W3093922502","https://openalex.org/W3094236223","https://openalex.org/W3100172161","https://openalex.org/W3104876774","https://openalex.org/W3111482008","https://openalex.org/W3129731039","https://openalex.org/W3133805463","https://openalex.org/W3134383769","https://openalex.org/W3170379366","https://openalex.org/W3201276701","https://openalex.org/W3204238384","https://openalex.org/W3206592106","https://openalex.org/W3206827162","https://openalex.org/W3212580602","https://openalex.org/W3216772467","https://openalex.org/W4200095173","https://openalex.org/W4200565903","https://openalex.org/W4206268535","https://openalex.org/W4233216703","https://openalex.org/W4285506274","https://openalex.org/W4313442619","https://openalex.org/W4367849444","https://openalex.org/W4383108338","https://openalex.org/W4392934329","https://openalex.org/W6801971982"],"related_works":["https://openalex.org/W2121300814","https://openalex.org/W4231091074","https://openalex.org/W1886613375","https://openalex.org/W4236081792","https://openalex.org/W4250583430","https://openalex.org/W4234406076","https://openalex.org/W2010731026","https://openalex.org/W4311328601","https://openalex.org/W2360893094","https://openalex.org/W4390787808"],"abstract_inverted_index":{"Abstract":[0],"The":[1,52,137,190],"requirement":[2],"for":[3,16,80,109,225],"a":[4,12,101,105,146,158,172],"high":[5],"number":[6],"of":[7,19,54,132],"training":[8],"episodes":[9,198,210],"has":[10,65],"been":[11,67],"major":[13],"limiting":[14],"factor":[15],"the":[17,43,70,85,122,129,133,154,187,202,223],"application":[18],"Reinforcement":[20],"Learning":[21,25],"(RL)":[22],"in":[23,57,153,195,208],"robotics.":[24],"skills":[26,56],"directly":[27,185],"on":[28,186],"real":[29,63,188],"robots":[30,64],"requires":[31],"time,":[32],"causes":[33],"wear":[34],"and":[35,37,45,59,74,94,117,124,127,141,161,171,201,217],"tear":[36],"can":[38,180],"lead":[39],"to":[40,42,48,62,92,120,166,183],"damage":[41],"robot":[44],"environment":[46,86],"due":[47],"unsafe":[49],"exploratory":[50],"actions.":[51],"success":[53],"learning":[55,135,148],"simulation":[58],"transferring":[60],"them":[61],"also":[66],"limited":[68],"by":[69,114,145,150],"gap":[71],"between":[72],"reality":[73],"simulation.":[75,226],"This":[76],"is":[77,193,206],"particularly":[78],"problematic":[79],"tasks":[81],"involving":[82],"contact":[83,88],"with":[84,213],"as":[87,168],"dynamics":[89],"are":[90,143],"hard":[91],"model":[93],"simulate.":[95],"In":[96],"this":[97],"paper":[98],"we":[99,175],"propose":[100],"framework":[102,108],"which":[103],"leverages":[104],"shared":[106],"control":[107],"modeling":[110],"known":[111],"constraints":[112],"defined":[113],"object":[115],"interactions":[116],"task":[118,139,160,164,192,205],"geometry":[119],"reduce":[121],"state":[123],"action":[125],"spaces":[126],"hence":[128],"overall":[130],"dimensionality":[131],"reinforcement":[134,147],"problem.":[136],"unknown":[138],"knowledge":[140],"actions":[142],"learned":[144,194,207],"agent":[149],"conducting":[151],"exploration":[152],"constrained":[155],"environment.":[156],"Using":[157],"pouring":[159,191],"grid-clamp":[162,203],"placement":[163,204],"(similar":[165],"peg-in-hole)":[167],"use":[169],"cases":[170],"7-DoF":[173],"arm,":[174],"show":[176],"that":[177],"our":[178],"approach":[179],"be":[181],"used":[182],"learn":[184],"robot.":[189],"only":[196],"65":[197],"(16":[199],"min)":[200,212],"75":[209],"(17":[211],"strong":[214],"safety":[215],"guarantees":[216],"simple":[218],"reward":[219],"functions,":[220],"greatly":[221],"alleviating":[222],"need":[224]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}