{"id":"https://openalex.org/W4396594865","doi":"https://doi.org/10.1109/lra.2024.3396368","title":"SRL-VIC: A Variable Stiffness-Based Safe Reinforcement Learning for Contact-Rich Robotic Tasks","display_name":"SRL-VIC: A Variable Stiffness-Based Safe Reinforcement Learning for Contact-Rich Robotic Tasks","publication_year":2024,"publication_date":"2024-05-02","ids":{"openalex":"https://openalex.org/W4396594865","doi":"https://doi.org/10.1109/lra.2024.3396368"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3396368","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2024.3396368","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/lra.2024.3396368","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102028476","display_name":"Heng Zhang","orcid":"https://orcid.org/0000-0003-4832-9668"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Heng Zhang","raw_affiliation_strings":["Human-Robot Interfaces and Interaction Lab, Istituto Italiano di Tecnologia, Genoa, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4832-9668","affiliations":[{"raw_affiliation_string":"Human-Robot Interfaces and Interaction Lab, Istituto Italiano di Tecnologia, Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078645934","display_name":"G\u00f6khan Solak","orcid":"https://orcid.org/0000-0001-6342-1345"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gokhan Solak","raw_affiliation_strings":["Human-Robot Interfaces and Interaction Lab, Istituto Italiano di Tecnologia, Genoa, Italy"],"raw_orcid":"https://orcid.org/0000-0001-6342-1345","affiliations":[{"raw_affiliation_string":"Human-Robot Interfaces and Interaction Lab, Istituto Italiano di Tecnologia, Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027158729","display_name":"Gustavo J. G. Lahr","orcid":"https://orcid.org/0000-0002-0403-991X"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gustavo J. G. Lahr","raw_affiliation_strings":["Human-Robot Interfaces and Interaction Lab, Istituto Italiano di Tecnologia, Genoa, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0403-991X","affiliations":[{"raw_affiliation_string":"Human-Robot Interfaces and Interaction Lab, Istituto Italiano di Tecnologia, Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070028115","display_name":"Arash Ajoudani","orcid":"https://orcid.org/0000-0002-1261-737X"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Arash Ajoudani","raw_affiliation_strings":["Human-Robot Interfaces and Interaction Lab, Istituto Italiano di Tecnologia, Genoa, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1261-737X","affiliations":[{"raw_affiliation_string":"Human-Robot Interfaces and Interaction Lab, Istituto Italiano di Tecnologia, Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I30771326"],"apc_list":null,"apc_paid":null,"fwci":2.1758,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.87355565,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"9","issue":"6","first_page":"5631","last_page":"5638"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10784","display_name":"Muscle activation and electromyography studies","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10784","display_name":"Muscle activation and electromyography studies","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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/T10338","display_name":"Advanced Sensor and Energy Harvesting Materials","score":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.47325021028518677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46845555305480957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47325021028518677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46845555305480957}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2024.3396368","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2024.3396368","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2406.13744","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.13744","pdf_url":"https://arxiv.org/pdf/2406.13744","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1109/lra.2024.3396368","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2024.3396368","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4219559521","display_name":"CONfigurable CollaborativE Robot Technologies","funder_award_id":"101016007","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4998061797","display_name":"Socio-physical Interaction Skills for Cooperative Human-Robot Systems in Agile Production","funder_award_id":"871237","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2014550481","https://openalex.org/W2074816318","https://openalex.org/W2090298673","https://openalex.org/W2289605848","https://openalex.org/W2765218414","https://openalex.org/W2791542133","https://openalex.org/W2795550549","https://openalex.org/W2973229164","https://openalex.org/W3003629310","https://openalex.org/W3012366945","https://openalex.org/W3115157241","https://openalex.org/W3130500701","https://openalex.org/W3130984490","https://openalex.org/W3150718622","https://openalex.org/W3195968524","https://openalex.org/W4206497039","https://openalex.org/W4221141160","https://openalex.org/W4221151401","https://openalex.org/W4285225245","https://openalex.org/W4287629996","https://openalex.org/W4383109202","https://openalex.org/W6747473740","https://openalex.org/W6784521679","https://openalex.org/W6784630725","https://openalex.org/W6784643869"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3,18],"emerged":[4],"as":[5],"a":[6,39,43,62,72,104,133,154],"promising":[7],"paradigm":[8],"in":[9,26,30,113],"complex":[10],"and":[11,69,106,128,140,165],"continuous":[12],"robotic":[13],"tasks,":[14],"however,":[15],"safe":[16,105],"exploration":[17],"been":[19],"one":[20],"of":[21,57,111],"the":[22,55,58,76,82,88,94,99,122,125,130],"main":[23],"challenges,":[24],"especially":[25],"contact-rich":[27,114],"manipulation":[28],"tasks":[29,116],"unstructured":[31],"environments.":[32],"Focusing":[33],"on":[34,148,153],"this":[35],"issue,":[36],"we":[37],"proposeSRL-VIC:":[38],"model-freesafeRLframework":[40],"combined":[41],"with":[42,163],"variable":[44],"impedance":[45],"controller":[46],"(VIC).":[47],"Specifically,safety":[48],"criticandrecovery":[49],"policynetworks":[50],"are":[51,84],"pre-trained":[52],"wheresafety":[53],"criticevaluates":[54],"safety":[56,141],"next":[59],"action":[60,74],"using":[61],"risk":[63,77],"value":[64,78],"before":[65],"it":[66],"is":[67,79,169],"executed":[68],"therecovery":[70],"policysuggests":[71],"corrective":[73],"if":[75],"high.":[80],"Furthermore,":[81],"policies":[83],"updated":[85],"online":[86],"where":[87],"task":[89,95,138,161],"policy":[90,146],"not":[91],"only":[92],"achieves":[93],"but":[96],"also":[97],"modulates":[98],"stiffness":[100],"parameters":[101],"to":[102],"keep":[103],"compliant":[107],"profile.":[108],"A":[109],"set":[110],"experiments":[112],"maze":[115],"demonstrate":[117],"that":[118],"our":[119,145],"framework":[120],"outperforms":[121],"baselines":[123],"(without":[124],"recovery":[126],"mechanism":[127],"without":[129,157],"VIC),":[131],"yielding":[132],"good":[134],"trade-off":[135],"between":[136],"efficient":[137],"accomplishment":[139],"guarantee.":[142],"We":[143],"show":[144],"trained":[147],"simulation":[149],"can":[150],"be":[151],"deployed":[152],"physical":[155],"robot":[156],"fine-tuning,":[158],"achieving":[159],"successful":[160],"completion":[162],"robustness":[164],"generalization.":[166],"The":[167],"video":[168],"available":[170],"athttps://youtu.be/ksWXR3vByoQ.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}