{"id":"https://openalex.org/W4385764218","doi":"https://doi.org/10.24963/ijcai.2023/790","title":"Q-Learning-Based Model Predictive Variable Impedance Control for Physical Human-Robot Collaboration (Extended Abstract)","display_name":"Q-Learning-Based Model Predictive Variable Impedance Control for Physical Human-Robot Collaboration (Extended Abstract)","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385764218","doi":"https://doi.org/10.24963/ijcai.2023/790"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/790","is_oa":false,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ijcai.org/proceedings/2023/0790.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086291668","display_name":"Loris Roveda","orcid":"https://orcid.org/0000-0002-4427-536X"},"institutions":[{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Loris Roveda","raw_affiliation_strings":["SUPSI/USI-IDSIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SUPSI/USI-IDSIA","institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103096181","display_name":"Andrea Testa","orcid":"https://orcid.org/0000-0001-9364-307X"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Testa","raw_affiliation_strings":["Politecnico di Milano","Politecnico di Milano, Department of Mechanical Engineering, via La Masa 1, 20156, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Politecnico di Milano, Department of Mechanical Engineering, via La Masa 1, 20156, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003810719","display_name":"Asad Ali Shahid","orcid":"https://orcid.org/0009-0001-0312-9657"},"institutions":[{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Asad Ali Shahid","raw_affiliation_strings":["SUPSI/USI-IDSIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SUPSI/USI-IDSIA","institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050750282","display_name":"Francesco Braghin","orcid":"https://orcid.org/0000-0002-0476-4118"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Braghin","raw_affiliation_strings":["Politecnico Di Milano","Politecnico di Milano, Department of Mechanical Engineering, via La Masa 1, 20156, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico Di Milano","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Politecnico di Milano, Department of Mechanical Engineering, via La Masa 1, 20156, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046585507","display_name":"Dario Piga","orcid":"https://orcid.org/0000-0001-7691-4886"},"institutions":[{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Dario Piga","raw_affiliation_strings":["SUPSI - IDSIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SUPSI - IDSIA","institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6959","last_page":"6963"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9819999933242798,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9819999933242798,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.957099974155426,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.95660001039505,"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/setpoint","display_name":"Setpoint","score":0.7715587019920349},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.6803776025772095},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6424915790557861},{"id":"https://openalex.org/keywords/impedance-control","display_name":"Impedance control","score":0.557616651058197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5553033351898193},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5321689248085022},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5099035501480103},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4844827353954315},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4384959042072296},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.4293237626552582},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.41315364837646484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4081072211265564},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.34456902742385864},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2968333661556244},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24281251430511475},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22853189706802368},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09557217359542847}],"concepts":[{"id":"https://openalex.org/C12302492","wikidata":"https://www.wikidata.org/wiki/Q1752097","display_name":"Setpoint","level":2,"score":0.7715587019920349},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.6803776025772095},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6424915790557861},{"id":"https://openalex.org/C2777984285","wikidata":"https://www.wikidata.org/wiki/Q17098134","display_name":"Impedance control","level":3,"score":0.557616651058197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5553033351898193},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5321689248085022},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5099035501480103},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4844827353954315},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4384959042072296},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.4293237626552582},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41315364837646484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4081072211265564},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.34456902742385864},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2968333661556244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24281251430511475},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22853189706802368},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09557217359542847},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2023/790","is_oa":false,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1263195","is_oa":true,"landing_page_url":"https://hdl.handle.net/11311/1263195","pdf_url":"https://www.ijcai.org/proceedings/2023/0790.pdf","source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"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/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:re.public.polimi.it:11311/1263195","is_oa":true,"landing_page_url":"https://hdl.handle.net/11311/1263195","pdf_url":"https://www.ijcai.org/proceedings/2023/0790.pdf","source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"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/conferenceObject"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G1389811400","display_name":null,"funder_award_id":"886977","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G7172734496","display_name":null,"funder_award_id":"886977","funder_id":"https://openalex.org/F4320320367","funder_display_name":"Cleansky"},{"id":"https://openalex.org/G7271342099","display_name":null,"funder_award_id":"E!115182","funder_id":"https://openalex.org/F4320338388","funder_display_name":"Eurostars"}],"funders":[{"id":"https://openalex.org/F4320320367","display_name":"Cleansky","ror":"https://ror.org/03nv0z257"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338388","display_name":"Eurostars","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385764218.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2606499982","https://openalex.org/W2888380943","https://openalex.org/W2907668458","https://openalex.org/W2910187114","https://openalex.org/W2944345882","https://openalex.org/W2965667459","https://openalex.org/W2982429175","https://openalex.org/W2999318559","https://openalex.org/W3004699108","https://openalex.org/W3012211643","https://openalex.org/W3035497536","https://openalex.org/W3085930940","https://openalex.org/W3090787630","https://openalex.org/W4239900805","https://openalex.org/W4291006859"],"related_works":["https://openalex.org/W2186176044","https://openalex.org/W2152422428","https://openalex.org/W2811393877","https://openalex.org/W2089203544","https://openalex.org/W2762381663","https://openalex.org/W1886477626","https://openalex.org/W4385196987","https://openalex.org/W1540467731","https://openalex.org/W218732962","https://openalex.org/W2538037439"],"abstract_inverted_index":{"Physical":[0],"human-robot":[1,69,124],"collaboration":[2,70],"is":[3,78,116,135,155],"increasingly":[4],"required":[5],"in":[6,44,67,99,165,205],"many":[7],"contexts.":[8],"To":[9],"implement":[10,81],"an":[11,111,170,183],"effective":[12],"collaboration,":[13],"the":[14,21,31,45,65,103,106,120,123,129,139,175,179],"robot":[15,84,211],"should":[16],"be":[17],"able":[18],"to":[19,63,80,101,118,173],"recognize":[20],"human\u2019s":[22],"intentions":[23],"and":[24,27,92,185,194],"guarantee":[25],"safe":[26],"adaptive":[28],"behavior":[29],"along":[30],"intended":[32],"motion":[33],"directions.":[34],"The":[35,86,132,153,196],"robot-control":[36],"strategies":[37],"with":[38,49,145],"such":[39],"attributes":[40],"are":[41,95],"particularly":[42],"demanded":[43],"industrial":[46],"field.":[47],"Indeed,":[48,178],"this":[50,52,109],"aim,":[51],"work":[53],"proposes":[54],"a":[55,161,207,216],"Q-Learning-based":[56],"Model":[57],"Predictive":[58],"Variable":[59],"Impedance":[60],"Control":[61],"(Q-LMPVIC)":[62],"assist":[64],"operators":[66],"physical":[68],"(pHRC)":[71],"tasks.":[72],"A":[73],"Cartesian":[74],"impedance":[75,87],"control":[76,88],"loop":[77],"designed":[79,117],"decoupled":[82],"compliant":[83],"dynamics.":[85],"parameters":[89],"(i.e.,":[90],"setpoint":[91],"damping":[93],"parameters)":[94],"then":[96,136],"optimized":[97],"online":[98,167],"order":[100],"maximize":[102],"performance":[104],"of":[105,113,122,150,160,191],"pHRC.":[107],"For":[108],"purpose,":[110],"ensemble":[112],"neural":[114],"networks":[115],"learn":[119],"modeling":[121,134],"interaction":[125],"dynamics":[126],"while":[127],"capturing":[128],"associated":[130],"uncertainties.":[131],"derived":[133],"exploited":[137],"by":[138,148,157],"model":[140],"predictive":[141],"controller":[142],"(MPC),":[143],"enhanced":[144],"stability":[146],"guarantees":[147],"means":[149],"Lyapunov":[151],"constraints.":[152],"MPC":[154],"solved":[156],"making":[158],"use":[159],"Q-Learning":[162],"method":[163,181],"that,":[164],"its":[166],"implementation,":[168],"uses":[169],"actor-critic":[171],"algorithm":[172],"approximate":[174],"exact":[176],"solution.":[177],"Q-learning":[180],"provides":[182],"accurate":[184],"highly":[186],"efficient":[187],"solution":[188],"(in":[189],"terms":[190],"computational":[192],"time":[193],"resources).":[195],"proposed":[197],"approach":[198],"has":[199,212],"been":[200,213],"validated":[201],"through":[202],"experimental":[203],"tests,":[204],"which":[206],"Franka":[208],"EMIKA":[209],"panda":[210],"used":[214],"as":[215],"test":[217],"platform.":[218]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2023-08-12T00:00:00"}