{"id":"https://openalex.org/W4221162322","doi":"https://doi.org/10.1109/robio55434.2022.10011996","title":"Skill-based Multi-objective Reinforcement Learning of Industrial Robot Tasks with Planning and Knowledge Integration","display_name":"Skill-based Multi-objective Reinforcement Learning of Industrial Robot Tasks with Planning and Knowledge Integration","publication_year":2022,"publication_date":"2022-12-05","ids":{"openalex":"https://openalex.org/W4221162322","doi":"https://doi.org/10.1109/robio55434.2022.10011996"},"language":"en","primary_location":{"id":"doi:10.1109/robio55434.2022.10011996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio55434.2022.10011996","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.10033","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077454772","display_name":"Matthias Mayr","orcid":"https://orcid.org/0000-0002-2780-1233"},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Matthias Mayr","raw_affiliation_strings":["Lund University,Faculty of Engineering (LTH),Department of Computer Science,Lund,SE,Sweden,22100"],"affiliations":[{"raw_affiliation_string":"Lund University,Faculty of Engineering (LTH),Department of Computer Science,Lund,SE,Sweden,22100","institution_ids":["https://openalex.org/I187531555"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033161877","display_name":"Faseeh Ahmad","orcid":"https://orcid.org/0000-0001-6236-3796"},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Faseeh Ahmad","raw_affiliation_strings":["Lund University,Faculty of Engineering (LTH),Department of Computer Science,Lund,SE,Sweden,22100"],"affiliations":[{"raw_affiliation_string":"Lund University,Faculty of Engineering (LTH),Department of Computer Science,Lund,SE,Sweden,22100","institution_ids":["https://openalex.org/I187531555"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048630321","display_name":"Konstantinos Chatzilygeroudis","orcid":"https://orcid.org/0000-0003-3585-1027"},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Konstantinos Chatzilygeroudis","raw_affiliation_strings":["University of Patras,Computer Engineering and Informatics Department (CEID),Greece"],"affiliations":[{"raw_affiliation_string":"University of Patras,Computer Engineering and Informatics Department (CEID),Greece","institution_ids":["https://openalex.org/I174878644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008975166","display_name":"Luigi Nardi","orcid":"https://orcid.org/0000-0002-4601-2264"},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Luigi Nardi","raw_affiliation_strings":["Lund University,Faculty of Engineering (LTH),Department of Computer Science,Lund,SE,Sweden,22100"],"affiliations":[{"raw_affiliation_string":"Lund University,Faculty of Engineering (LTH),Department of Computer Science,Lund,SE,Sweden,22100","institution_ids":["https://openalex.org/I187531555"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075432056","display_name":"Volker Kr\u00fcger","orcid":"https://orcid.org/0000-0002-8836-8816"},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Volker Krueger","raw_affiliation_strings":["Lund University,Faculty of Engineering (LTH),Department of Computer Science,Lund,SE,Sweden,22100"],"affiliations":[{"raw_affiliation_string":"Lund University,Faculty of Engineering (LTH),Department of Computer Science,Lund,SE,Sweden,22100","institution_ids":["https://openalex.org/I187531555"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5077454772"],"corresponding_institution_ids":["https://openalex.org/I187531555"],"apc_list":null,"apc_paid":null,"fwci":0.7072,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56705173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1995","last_page":"2002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8583999872207642,"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":0.8583999872207642,"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":0.09939999878406525,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.005900000222027302,"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":0.7596451044082642},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.64530348777771},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6414811611175537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5724186301231384},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5487351417541504},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5319842100143433},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5178694725036621},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5138599872589111},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.45448705554008484},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.41511720418930054},{"id":"https://openalex.org/keywords/performance-indicator","display_name":"Performance indicator","score":0.41254866123199463},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37946417927742004},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14470767974853516},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.08753743767738342},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08321374654769897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596451044082642},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.64530348777771},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6414811611175537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5724186301231384},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5487351417541504},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5319842100143433},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5178694725036621},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5138599872589111},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.45448705554008484},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.41511720418930054},{"id":"https://openalex.org/C135510737","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance indicator","level":2,"score":0.41254866123199463},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37946417927742004},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14470767974853516},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.08753743767738342},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08321374654769897},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/robio55434.2022.10011996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio55434.2022.10011996","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2203.10033","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.10033","pdf_url":"https://arxiv.org/pdf/2203.10033","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:lup.lub.lu.se:57122c71-3201-4d86-85a9-00b3b51935f3","is_oa":false,"landing_page_url":"https://lup.lub.lu.se/record/57122c71-3201-4d86-85a9-00b3b51935f3","pdf_url":null,"source":{"id":"https://openalex.org/S4306400536","display_name":"Lund University Publications (Lund University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I187531555","host_organization_name":"Lund University","host_organization_lineage":["https://openalex.org/I187531555"],"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":"text"},{"id":"doi:10.48550/arxiv.2203.10033","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.10033","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.10033","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.10033","pdf_url":"https://arxiv.org/pdf/2203.10033","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316785","display_name":"VMware","ror":null},{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320330001","display_name":"Ant Financial Services Group","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4221162322.pdf","grobid_xml":"https://content.openalex.org/works/W4221162322.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1972524121","https://openalex.org/W1978161072","https://openalex.org/W2055362048","https://openalex.org/W2098564375","https://openalex.org/W2108513714","https://openalex.org/W2116226448","https://openalex.org/W2119709400","https://openalex.org/W2136719407","https://openalex.org/W2171246729","https://openalex.org/W2308567354","https://openalex.org/W2313961224","https://openalex.org/W2511419816","https://openalex.org/W2550336733","https://openalex.org/W2586181036","https://openalex.org/W2604883922","https://openalex.org/W2618505680","https://openalex.org/W2622877735","https://openalex.org/W2727037355","https://openalex.org/W2773249613","https://openalex.org/W2905099814","https://openalex.org/W2909851421","https://openalex.org/W2963709735","https://openalex.org/W2976305354","https://openalex.org/W2995983596","https://openalex.org/W2997896361","https://openalex.org/W3003524200","https://openalex.org/W3003629310","https://openalex.org/W3138524621","https://openalex.org/W3145123113","https://openalex.org/W3203483019","https://openalex.org/W3204329301","https://openalex.org/W4312641024","https://openalex.org/W6653548176","https://openalex.org/W6675200109","https://openalex.org/W6680657880","https://openalex.org/W6753051720","https://openalex.org/W6755800398","https://openalex.org/W6757333043","https://openalex.org/W6788170692"],"related_works":["https://openalex.org/W1353223","https://openalex.org/W868042","https://openalex.org/W929682","https://openalex.org/W162356","https://openalex.org/W1279312","https://openalex.org/W10379689","https://openalex.org/W7430954","https://openalex.org/W6915741","https://openalex.org/W5176077","https://openalex.org/W10377101"],"abstract_inverted_index":{"In":[0],"modern":[1],"industrial":[2],"settings":[3],"with":[4,54,124],"small":[5],"batch":[6],"sizes":[7],"it":[8,31],"should":[9],"be":[10],"easy":[11],"to":[12,33,128,133,145],"set":[13],"up":[14],"a":[15,19,49,71,80,83,125,166,200],"robot":[16,212],"system":[17],"for":[18,60,108,136,189],"new":[20],"task.":[21],"Strategies":[22],"exist,":[23],"e.g.":[24],"the":[25,65,68,75,90,94,109,178,207],"use":[26],"of":[27,51,57,85,93,114,182],"skills,":[28],"but":[29],"when":[30],"comes":[32],"handling":[34],"forces":[35],"and":[36,89,106,132,154,171,180,205],"torques,":[37],"these":[38],"systems":[39],"often":[40,160],"fall":[41],"short.":[42],"We":[43,63,164,176,194],"introduce":[44],"an":[45,101],"approach":[46,170,184],"that":[47],"provides":[48,70],"combination":[50],"task-level":[52],"planning":[53,76,131],"targeted":[55],"learning":[56,110,120,186],"scenario-specific":[58],"parameters":[59,92,107,188],"skill-based":[61],"systems.":[62],"propose":[64],"following":[66],"pipeline:":[67],"user":[69],"task":[72,155],"goal":[73],"in":[74,174],"language":[77],"PDDL,":[78],"then":[79],"plan":[81],"(i.e.,":[82],"sequence":[84],"skills)":[86],"is":[87,121],"generated":[88],"learnable":[91],"skills":[95],"are":[96,117],"automatically":[97],"identified,":[98],"and,":[99],"finally,":[100],"operator":[102],"chooses":[103],"reward":[104],"functions":[105],"process.":[111],"Two":[112],"aspects":[113],"our":[115,183],"methodology":[116],"critical:":[118],"(a)":[119],"tightly":[122],"integrated":[123],"knowledge":[126],"framework":[127],"support":[129],"symbolic":[130],"provide":[134],"priors":[135],"learning,":[137],"(b)":[138],"using":[139],"multi-objective":[140,167],"optimization.":[141],"This":[142],"can":[143,159],"help":[144],"balance":[146],"key":[147],"performance":[148,156],"indicators":[149],"(KPIs)":[150],"such":[151],"as":[152],"safety":[153],"since":[157],"they":[158],"affect":[161],"each":[162],"other.":[163],"adopt":[165],"Bayesian":[168],"optimization":[169],"learn":[172],"entirely":[173],"simulation.":[175],"demonstrate":[177],"efficacy":[179],"versatility":[181],"by":[185,210],"skill":[187],"two":[190],"different":[191],"contact-rich":[192],"tasks.":[193],"show":[195],"their":[196],"successful":[197],"execution":[198],"on":[199],"real":[201],"7-DOF":[202],"KUKA-iiwa":[203],"manipulator":[204],"outperform":[206],"manual":[208],"parameterization":[209],"human":[211],"operators.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-04-03T00:00:00"}