{"id":"https://openalex.org/W4327733733","doi":"https://doi.org/10.1007/s13042-023-01815-8","title":"Learning positioning policies for mobile manipulation operations with deep reinforcement learning","display_name":"Learning positioning policies for mobile manipulation operations with deep reinforcement learning","publication_year":2023,"publication_date":"2023-03-17","ids":{"openalex":"https://openalex.org/W4327733733","doi":"https://doi.org/10.1007/s13042-023-01815-8"},"language":"en","primary_location":{"id":"doi:10.1007/s13042-023-01815-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13042-023-01815-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13042-023-01815-8.pdf","source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"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":"International Journal of Machine Learning and Cybernetics","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/s13042-023-01815-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017407317","display_name":"Ander Iriondo","orcid":"https://orcid.org/0000-0003-2760-435X"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]},{"id":"https://openalex.org/I4210136402","display_name":"Tekniker","ror":"https://ror.org/033vryh36","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210136402"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Ander Iriondo","raw_affiliation_strings":["Department of Autonomous and Intelligent Systems, Tekniker - Basque Research and Technology Alliance (BRTA), I\u00f1aki Goenaga, 5, 20600, Eibar, Gipuzkoa, Spain","Robotics and Autonomous Systems group (RSAIT), Department of Computer Science and Artificial Intelligence, University of the Basque Country (UPV/EHU), Po Manuel Lardizabal,1, 20018, Donostia-San Sebasti\u00e1n, Gipuzkoa, Spain"],"raw_orcid":"https://orcid.org/0000-0003-2760-435X","affiliations":[{"raw_affiliation_string":"Department of Autonomous and Intelligent Systems, Tekniker - Basque Research and Technology Alliance (BRTA), I\u00f1aki Goenaga, 5, 20600, Eibar, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210136402"]},{"raw_affiliation_string":"Robotics and Autonomous Systems group (RSAIT), Department of Computer Science and Artificial Intelligence, University of the Basque Country (UPV/EHU), Po Manuel Lardizabal,1, 20018, Donostia-San Sebasti\u00e1n, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082262750","display_name":"Elena Lazkano","orcid":"https://orcid.org/0000-0002-7653-6210"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Elena Lazkano","raw_affiliation_strings":["Robotics and Autonomous Systems group (RSAIT), Department of Computer Science and Artificial Intelligence, University of the Basque Country (UPV/EHU), Po Manuel Lardizabal,1, 20018, Donostia-San Sebasti\u00e1n, Gipuzkoa, Spain"],"raw_orcid":"https://orcid.org/0000-0002-7653-6210","affiliations":[{"raw_affiliation_string":"Robotics and Autonomous Systems group (RSAIT), Department of Computer Science and Artificial Intelligence, University of the Basque Country (UPV/EHU), Po Manuel Lardizabal,1, 20018, Donostia-San Sebasti\u00e1n, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002524622","display_name":"Ander Ansuategi","orcid":"https://orcid.org/0000-0001-9777-9564"},"institutions":[{"id":"https://openalex.org/I4210136402","display_name":"Tekniker","ror":"https://ror.org/033vryh36","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210136402"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ander Ansuategi","raw_affiliation_strings":["Department of Autonomous and Intelligent Systems, Tekniker - Basque Research and Technology Alliance (BRTA), I\u00f1aki Goenaga, 5, 20600, Eibar, Gipuzkoa, Spain"],"raw_orcid":"https://orcid.org/0000-0001-9777-9564","affiliations":[{"raw_affiliation_string":"Department of Autonomous and Intelligent Systems, Tekniker - Basque Research and Technology Alliance (BRTA), I\u00f1aki Goenaga, 5, 20600, Eibar, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210136402"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004882229","display_name":"Andoni Rivera","orcid":"https://orcid.org/0000-0001-8550-5312"},"institutions":[{"id":"https://openalex.org/I4210136402","display_name":"Tekniker","ror":"https://ror.org/033vryh36","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210136402"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Andoni Rivera","raw_affiliation_strings":["Department of Autonomous and Intelligent Systems, Tekniker - Basque Research and Technology Alliance (BRTA), I\u00f1aki Goenaga, 5, 20600, Eibar, Gipuzkoa, Spain"],"raw_orcid":"https://orcid.org/0000-0001-8550-5312","affiliations":[{"raw_affiliation_string":"Department of Autonomous and Intelligent Systems, Tekniker - Basque Research and Technology Alliance (BRTA), I\u00f1aki Goenaga, 5, 20600, Eibar, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210136402"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008870803","display_name":"Iker Lluvia","orcid":"https://orcid.org/0000-0001-9192-3879"},"institutions":[{"id":"https://openalex.org/I4210136402","display_name":"Tekniker","ror":"https://ror.org/033vryh36","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210136402"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Iker Lluvia","raw_affiliation_strings":["Department of Autonomous and Intelligent Systems, Tekniker - Basque Research and Technology Alliance (BRTA), I\u00f1aki Goenaga, 5, 20600, Eibar, Gipuzkoa, Spain"],"raw_orcid":"https://orcid.org/0000-0001-9192-3879","affiliations":[{"raw_affiliation_string":"Department of Autonomous and Intelligent Systems, Tekniker - Basque Research and Technology Alliance (BRTA), I\u00f1aki Goenaga, 5, 20600, Eibar, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210136402"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034934100","display_name":"Carlos Tub\u00edo","orcid":"https://orcid.org/0000-0002-3763-5312"},"institutions":[{"id":"https://openalex.org/I4210136402","display_name":"Tekniker","ror":"https://ror.org/033vryh36","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210136402"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carlos Tub\u00edo","raw_affiliation_strings":["Department of Autonomous and Intelligent Systems, Tekniker - Basque Research and Technology Alliance (BRTA), I\u00f1aki Goenaga, 5, 20600, Eibar, Gipuzkoa, Spain"],"raw_orcid":"https://orcid.org/0000-0002-3763-5312","affiliations":[{"raw_affiliation_string":"Department of Autonomous and Intelligent Systems, Tekniker - Basque Research and Technology Alliance (BRTA), I\u00f1aki Goenaga, 5, 20600, Eibar, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210136402"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5017407317"],"corresponding_institution_ids":["https://openalex.org/I169108374","https://openalex.org/I4210136402"],"apc_list":{"value":2790,"currency":"EUR","value_usd":3590},"apc_paid":{"value":2790,"currency":"EUR","value_usd":3590},"fwci":3.9455,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93952067,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"14","issue":"9","first_page":"3003","last_page":"3023"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8290314674377441},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6635952591896057},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.6414927244186401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5366306900978088},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36796045303344727}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8290314674377441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6635952591896057},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.6414927244186401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5366306900978088},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36796045303344727}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s13042-023-01815-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13042-023-01815-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13042-023-01815-8.pdf","source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"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":"International Journal of Machine Learning and Cybernetics","raw_type":"journal-article"},{"id":"pmh:oai:addi.ehu.eus:10810/66934","is_oa":true,"landing_page_url":"http://hdl.handle.net/10810/66934","pdf_url":"http://addi.ehu.es/bitstream/10810/66934/1/s13042-023-01815-8.pdf","source":{"id":"https://openalex.org/S4306401964","display_name":"Communities in ADDI (University of the Basque Country)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169108374","host_organization_name":"University of the Basque Country","host_organization_lineage":["https://openalex.org/I169108374"],"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":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s13042-023-01815-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13042-023-01815-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13042-023-01815-8.pdf","source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"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":"International Journal of Machine Learning and Cybernetics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1303858915","display_name":null,"funder_award_id":"CER-20211007","funder_id":"https://openalex.org/F4320321043","funder_display_name":"Centro para el Desarrollo Tecnol\u00f3gico Industrial"},{"id":"https://openalex.org/G3777950849","display_name":null,"funder_award_id":"KK-2021","funder_id":"https://openalex.org/F4320321705","funder_display_name":"Eusko Jaurlaritza"},{"id":"https://openalex.org/G7360475266","display_name":null,"funder_award_id":"KK-2021/00033","funder_id":"https://openalex.org/F4320321705","funder_display_name":"Eusko Jaurlaritza"},{"id":"https://openalex.org/G7419420291","display_name":null,"funder_award_id":"KK-2021/00033 TREBEZIA","funder_id":"https://openalex.org/F4320323050","funder_display_name":"Ekonomiaren Garapen eta Lehiakortasun Saila, Eusko Jaurlaritza"}],"funders":[{"id":"https://openalex.org/F4320321043","display_name":"Centro para el Desarrollo Tecnol\u00f3gico Industrial","ror":"https://ror.org/0124x7055"},{"id":"https://openalex.org/F4320321705","display_name":"Eusko Jaurlaritza","ror":"https://ror.org/00pz2fp31"},{"id":"https://openalex.org/F4320323050","display_name":"Ekonomiaren Garapen eta Lehiakortasun Saila, Eusko Jaurlaritza","ror":"https://ror.org/007xj0t96"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4327733733.pdf"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W59183349","https://openalex.org/W1577509784","https://openalex.org/W1639770520","https://openalex.org/W1971355878","https://openalex.org/W1972267259","https://openalex.org/W1984461808","https://openalex.org/W2006905283","https://openalex.org/W2016505519","https://openalex.org/W2048084888","https://openalex.org/W2091085232","https://openalex.org/W2096636372","https://openalex.org/W2110160528","https://openalex.org/W2130422193","https://openalex.org/W2145339207","https://openalex.org/W2148643450","https://openalex.org/W2166362129","https://openalex.org/W2296055201","https://openalex.org/W2493095453","https://openalex.org/W2738642082","https://openalex.org/W2739330054","https://openalex.org/W2775416623","https://openalex.org/W2907537824","https://openalex.org/W2907916537","https://openalex.org/W2911426134","https://openalex.org/W2963428623","https://openalex.org/W2964083861","https://openalex.org/W2999969016","https://openalex.org/W3005451807","https://openalex.org/W3005698582","https://openalex.org/W3041202696","https://openalex.org/W3090299930","https://openalex.org/W3090809286","https://openalex.org/W3091544428","https://openalex.org/W3100789280","https://openalex.org/W3123675609","https://openalex.org/W3126321819","https://openalex.org/W3158253560","https://openalex.org/W3198377903","https://openalex.org/W3204493217","https://openalex.org/W3206969627","https://openalex.org/W4210613326","https://openalex.org/W4285102554","https://openalex.org/W6868356770"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Abstract":[0],"This":[1,41],"work":[2,42,190],"focuses":[3],"on":[4,11,55],"the":[5,30,35,39,48,53,71,78,81,91,100,103,116,133,136,150,159,184,188,194,199,213,226,234],"operation":[6],"of":[7,38,51,115,196,220,245],"picking":[8],"an":[9,216],"object":[10],"a":[12,15,26,56,106,112,168,204,241],"table":[13],"with":[14,47,187,212,215],"mobile":[16],"manipulator.":[17],"We":[18,166,182],"use":[19],"deep":[20],"reinforcement":[21],"learning":[22],"(DRL)":[23],"to":[24,69,89,94,157,164,203],"learn":[25],"positioning":[27],"policy":[28],"for":[29,131,171],"robot\u2019s":[31],"base":[32,72,92,134,161],"by":[33],"considering":[34],"reachability":[36],"constraints":[37],"arm.":[40],"extends":[43],"our":[44],"first":[45,109],"proof-of-concept":[46],"ultimate":[49],"goal":[50],"validating":[52],"method":[54,186],"real":[57,235],"robot.":[58],"Twin":[59],"Delayed":[60],"Deep":[61],"Deterministic":[62],"Policy":[63],"Gradient":[64],"(TD3)":[65],"algorithm":[66],"is":[67,75,88,144,229],"used":[68],"model":[70],"controller,":[73],"and":[74,121,135,152,179,191,198,231],"optimised":[76],"using":[77],"feedback":[79],"from":[80],"MoveIt!":[82],"based":[83],"arm":[84,101,137],"planner.":[85],"The":[86,129,141],"idea":[87],"encourage":[90],"controller":[93,162],"position":[95],"itself":[96],"in":[97,119,124,146,233],"areas":[98],"where":[99,238],"reaches":[102],"object.":[104],"Following":[105],"simulation-to-reality":[107],"approach,":[108],"we":[110,239],"create":[111],"realistic":[113],"simulation":[114,147],"robotic":[117,236],"environment":[118],"Unity,":[120],"integrate":[122],"it":[123],"Robot":[125],"Operating":[126],"System":[127],"(ROS).":[128],"drivers":[130],"both":[132,149],"are":[138,155],"also":[139],"implemented.":[140],"DRL-based":[142],"agent":[143,228],"trained":[145],"and,":[148],"robot":[151],"target":[153],"poses":[154],"randomised":[156],"make":[158],"learnt":[160,227],"robust":[163],"uncertainties.":[165],"propose":[167],"task-specific":[169],"setup":[170,201],"TD3,":[172],"which":[173],"includes":[174],"state/action":[175],"spaces,":[176],"reward":[177],"function":[178],"neural":[180],"architectures.":[181],"compare":[183],"proposed":[185,200],"baseline":[189],"show":[192],"that":[193],"combination":[195],"TD3":[197],"leads":[202],"$$11\\%$$":[205],"<mml:math":[206,222,247],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"><mml:mrow><mml:mn>11</mml:mn><mml:mo>%</mml:mo></mml:mrow></mml:math>":[207],"higher":[208],"success":[209,218,243],"rate":[210,219,244],"than":[211],"baseline,":[214],"overall":[217],"$$97\\%$$":[221],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"><mml:mrow><mml:mn>97</mml:mn><mml:mo>%</mml:mo></mml:mrow></mml:math>":[223],".":[224,249],"Finally,":[225],"deployed":[230],"validated":[232],"system":[237],"obtain":[240],"promising":[242],"$$75\\%$$":[246],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"><mml:mrow><mml:mn>75</mml:mn><mml:mo>%</mml:mo></mml:mrow></mml:math>":[248]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2023-03-18T00:00:00"}
