{"id":"https://openalex.org/W4412403875","doi":"https://doi.org/10.1109/lra.2025.3589162","title":"Towards Autonomous Reinforcement Learning for Real-World Robotic Manipulation With Large Language Models","display_name":"Towards Autonomous Reinforcement Learning for Real-World Robotic Manipulation With Large Language Models","publication_year":2025,"publication_date":"2025-07-14","ids":{"openalex":"https://openalex.org/W4412403875","doi":"https://doi.org/10.1109/lra.2025.3589162"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3589162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3589162","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031690340","display_name":"Niccol\u00f2 Turcato","orcid":"https://orcid.org/0000-0002-2995-4110"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Niccol\u00f2 Turcato","raw_affiliation_strings":["Department of Information Engineering, University of Padova, Padova, Italy","Department of Information Engineering, University of Padova, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2995-4110","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":"Department of Information Engineering, University of Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008610224","display_name":"Matteo Iovino","orcid":"https://orcid.org/0000-0002-6119-6399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matteo Iovino","raw_affiliation_strings":["ABB Corporate Research, Västerås, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-6119-6399","affiliations":[{"raw_affiliation_string":"ABB Corporate Research, Västerås, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086354913","display_name":"Aris Synodinos","orcid":"https://orcid.org/0000-0002-9217-909X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aris Synodinos","raw_affiliation_strings":["ABB Corporate Research, Västerås, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ABB Corporate Research, Västerås, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040482614","display_name":"Alberto Dalla Libera","orcid":"https://orcid.org/0000-0002-7656-7797"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Dalla Libera","raw_affiliation_strings":["Department of Information Engineering, University of Padova, Padova, Italy","Department of Information Engineering, University of Padova, Italy"],"raw_orcid":"https://orcid.org/0000-0002-7656-7797","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":"Department of Information Engineering, University of Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089846134","display_name":"Ruggero Carli","orcid":"https://orcid.org/0000-0002-6506-5898"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ruggero Carli","raw_affiliation_strings":["Department of Information Engineering, University of Padova, Padova, Italy","Department of Information Engineering, University of Padova, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6506-5898","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":"Department of Information Engineering, University of Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076700669","display_name":"Pietro Falco","orcid":"https://orcid.org/0000-0003-1133-0884"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pietro Falco","raw_affiliation_strings":["Department of Information Engineering, University of Padova, Padova, Italy","Department of Information Engineering, University of Padova, Italy"],"raw_orcid":"https://orcid.org/0000-0003-1133-0884","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":"Department of Information Engineering, University of Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5021,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82040333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"10","issue":"9","first_page":"8850","last_page":"8857"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.942799985408783,"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":0.942799985408783,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7028659582138062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5853071808815002},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.45546823740005493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4299914538860321}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7028659582138062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5853071808815002},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45546823740005493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4299914538860321}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2025.3589162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3589162","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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:www.research.unipd.it:11577/3560247","is_oa":false,"landing_page_url":"https://hdl.handle.net/11577/3560247","pdf_url":null,"source":{"id":"https://openalex.org/S4306402547","display_name":"Padua Research Archive (University of Padova)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"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":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2126909264","https://openalex.org/W3091037773","https://openalex.org/W3119264617","https://openalex.org/W3189223768","https://openalex.org/W4224912544","https://openalex.org/W4297964528","https://openalex.org/W4360584316","https://openalex.org/W4383097638","https://openalex.org/W4383108457","https://openalex.org/W4385473486","https://openalex.org/W4391128534","https://openalex.org/W4396877948","https://openalex.org/W4399374221","https://openalex.org/W4401415522","https://openalex.org/W4402354036","https://openalex.org/W4402716047","https://openalex.org/W4406415458","https://openalex.org/W4408757728","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6757592117","https://openalex.org/W6784257307","https://openalex.org/W6793159708","https://openalex.org/W6796168157","https://openalex.org/W6800774826","https://openalex.org/W6849861922","https://openalex.org/W6850790624","https://openalex.org/W6853664340","https://openalex.org/W6854422757","https://openalex.org/W6857151620","https://openalex.org/W6857415689","https://openalex.org/W6858636673","https://openalex.org/W6862908462","https://openalex.org/W6867621267","https://openalex.org/W6873385004","https://openalex.org/W6873570788","https://openalex.org/W6873762109"],"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":{"Recent":[0],"advancements":[1],"in":[2,50,101],"Large":[3],"Language":[4,9],"Models":[5,10],"(LLMs)":[6],"and":[7,37,58,147,160],"Visual":[8],"(VLMs)":[11],"have":[12],"significantly":[13],"impacted":[14],"robotics,":[15],"enabling":[16],"high-level":[17],"semantic":[18],"motion":[19],"planning":[20],"applications.":[21],"Reinforcement":[22,69],"Learning":[23],"(RL),":[24],"a":[25,80,124],"complementary":[26],"paradigm,":[27],"enables":[28],"agents":[29,100],"to":[30,83,97,111],"autonomously":[31],"optimize":[32],"complex":[33],"behaviors":[34],"through":[35,141],"interaction":[36],"reward":[38,43,85,108],"signals.":[39],"However,":[40],"designing":[41],"effective":[42],"functions":[44,86],"for":[45,71,129],"RL":[46,99],"remains":[47],"challenging,":[48],"especially":[49],"real-world":[51],"tasks":[52,150],"where":[53,104],"sparse":[54],"rewards":[55,60,94],"are":[56,95,163],"insufficient":[57],"dense":[59],"require":[61],"elaborate":[62],"design.":[63],"In":[64],"this":[65],"work,":[66],"we":[67,105],"proposeAutonomous":[68],"learning":[70],"Complex":[72],"Human-Informed":[73],"Environments(ARCHIE),":[74],"an":[75,152],"unsupervised":[76],"pipeline":[77],"leveraging":[78],"GPT-4,":[79],"pre-trained":[81],"LLM,":[82],"generate":[84],"directly":[87],"from":[88],"natural":[89],"language":[90],"task":[91,120],"descriptions.":[92],"The":[93],"used":[96],"train":[98],"simulated":[102,143],"environments,":[103],"formalize":[106],"the":[107,117,166],"generation":[109],"process":[110],"enhance":[112],"feasibility.":[113],"Additionally,":[114],"GPT-4":[115],"automates":[116],"coding":[118],"of":[119],"success":[121],"criteria,":[122],"creating":[123],"fully":[125],"automated,":[126],"one-shot":[127],"procedure":[128],"translating":[130],"human-readable":[131],"text":[132],"into":[133],"deployable":[134],"robot":[135,168],"skills.":[136],"Our":[137],"approach":[138],"is":[139],"validated":[140],"extensive":[142],"experiments":[144],"on":[145,165],"single-arm":[146],"bi-manual":[148],"manipulation":[149],"using":[151],"ABB":[153],"YuMi":[154],"collaborative":[155],"robot,":[156],"highlighting":[157],"its":[158],"practicality":[159],"effectiveness.":[161],"Tasks":[162],"demonstrated":[164],"real":[167],"setup.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}