{"id":"https://openalex.org/W7204168838","doi":"https://doi.org/10.1109/aim65483.2026.11658256","title":"Enhancing Sim2Real Transfer for Torque-Controlled Robots through Real2Sim Dynamics Estimation and Reinforcement Learning","display_name":"Enhancing Sim2Real Transfer for Torque-Controlled Robots through Real2Sim Dynamics Estimation and Reinforcement Learning","publication_year":2026,"publication_date":"2026-07-01","ids":{"openalex":"https://openalex.org/W7204168838","doi":"https://doi.org/10.1109/aim65483.2026.11658256"},"language":"en","primary_location":{"id":"doi:10.1109/aim65483.2026.11658256","doi":"https://doi.org/10.1109/aim65483.2026.11658256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aim65483.2026.11658256","pdf_url":null,"source":{"id":"https://openalex.org/S4393918220","display_name":"IEEE/ASME International Conference on Advanced Intelligent Mechatronics","issn_l":"2159-6247","issn":["2159-6247"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"2026 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22629","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115717706","display_name":"Davide Bargellini","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Bargellini","raw_affiliation_strings":["University of Bologna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bologna","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111296994","display_name":"Alex Pasquali","orcid":"https://orcid.org/0009-0005-6152-2528","observed_orcids":["https://orcid.org/0009-0005-6152-2528"]},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alex Pasquali","raw_affiliation_strings":["University of Bologna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bologna","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106662306","display_name":"Andrea Govoni","orcid":"https://orcid.org/0009-0002-4092-637X","observed_orcids":["https://orcid.org/0009-0002-4092-637X"]},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Govoni","raw_affiliation_strings":["University of Bologna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bologna","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078800000","display_name":"Riccardo Zanella","orcid":"https://orcid.org/0000-0001-5764-9896","observed_orcids":["https://orcid.org/0000-0001-5764-9896"]},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Riccardo Zanella","raw_affiliation_strings":["University of Twente"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Twente","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038240894","display_name":"Gianluca Palli","orcid":"https://orcid.org/0000-0001-9457-4643","observed_orcids":["https://orcid.org/0000-0001-9457-4643"]},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gianluca Palli","raw_affiliation_strings":["University of Bologna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bologna","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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/T10653","display_name":"Robot Manipulation and Learning","score":9.999999747378752e-05,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.8809999823570251},{"id":"https://openalex.org/keywords/torque-control","display_name":"torque control","score":0.8650000095367432},{"id":"https://openalex.org/keywords/robot-manipulators","display_name":"robot manipulators","score":0.6940000057220459},{"id":"https://openalex.org/keywords/trajectory-matching","display_name":"trajectory matching","score":0.6740000247955322},{"id":"https://openalex.org/keywords/genetic-algorithm-parameter-optimization","display_name":"genetic algorithm parameter optimization","score":0.7929999828338623},{"id":"https://openalex.org/keywords/domain-randomization","display_name":"domain randomization","score":0.996999979019165},{"id":"https://openalex.org/keywords/franka-emika-panda","display_name":"Franka Emika Panda","score":0.8700000047683716},{"id":"https://openalex.org/keywords/gravity-compensation","display_name":"gravity compensation","score":0.7549999952316284},{"id":"https://openalex.org/keywords/policy-robustness","display_name":"policy robustness","score":0.6019999980926514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5745999813079834},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5619999766349792},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4805000126361847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4472000002861023},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3984000086784363},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3801000118255615},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.37959998846054077},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.32269999384880066},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28049999475479126},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.26089999079704285}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/aim65483.2026.11658256","doi":"https://doi.org/10.1109/aim65483.2026.11658256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aim65483.2026.11658256","pdf_url":null,"source":{"id":"https://openalex.org/S4393918220","display_name":"IEEE/ASME International Conference on Advanced Intelligent Mechatronics","issn_l":"2159-6247","issn":["2159-6247"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"2026 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.22629","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22629","pdf_url":"https://arxiv.org/pdf/2608.22629","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22629","doi":"https://doi.org/10.48550/arxiv.2608.22629","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22629","pdf_url":null,"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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.22629","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22629","pdf_url":"https://arxiv.org/pdf/2608.22629","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204168838.pdf","grobid_xml":"https://content.openalex.org/works/W7204168838.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1481659984","https://openalex.org/W2173248099","https://openalex.org/W2767050701","https://openalex.org/W2897345632","https://openalex.org/W2964222556","https://openalex.org/W2968268581","https://openalex.org/W3035497536","https://openalex.org/W3088310808","https://openalex.org/W3114446492","https://openalex.org/W3207591725","https://openalex.org/W4308437157","https://openalex.org/W4376274293","https://openalex.org/W4385482448","https://openalex.org/W4385756663","https://openalex.org/W4401752050","https://openalex.org/W4405927045","https://openalex.org/W4405927125","https://openalex.org/W4416748401"],"related_works":["https://openalex.org/W7043243894","https://openalex.org/W4385756663","https://openalex.org/W4408999339","https://openalex.org/W2767050701","https://openalex.org/W7118162210","https://openalex.org/W2980820015","https://openalex.org/W3207591725","https://openalex.org/W2795341696","https://openalex.org/W3008492644","https://openalex.org/W2890728188"],"abstract_inverted_index":{"Transferring":[0],"reinforcement":[1,96,162],"learning":[2,97,163],"policies":[3],"from":[4,138],"simulation":[5,139],"to":[6,27,92,140],"Real-World":[7,142],"robots":[8],"remains":[9],"a":[10,37,94,122],"major":[11],"challenge,":[12],"particularly":[13],"when":[14],"dealing":[15],"with":[16,134],"low-level":[17],"torque":[18],"control,":[19],"where":[20],"even":[21],"small":[22],"modelling":[23,155],"inaccuracies":[24],"can":[25],"lead":[26],"unstable":[28],"or":[29],"unsafe":[30],"behaviours.":[31],"In":[32],"this":[33],"work,":[34],"we":[35,67],"propose":[36],"Real2Sim2Real":[38],"pipeline":[39],"that":[40],"improves":[41],"Sim2Real":[42],"transfer":[43,137],"for":[44],"torque-controlled":[45],"robotic":[46],"arms":[47],"by":[48,76],"combining":[49],"trajectory":[50],"matching,":[51],"parameter":[52,132],"optimization":[53],"via":[54],"genetic":[55],"algorithms,":[56],"and":[57,72,82,109,112,128,159],"domain":[58],"randomization.":[59],"Using":[60],"the":[61,78,116,141,150],"7-DOF":[62],"Franka":[63],"Emika":[64],"Panda":[65],"robot,":[66],"first":[68],"identify":[69],"friction,":[70],"inertia,":[71],"gravity":[73],"compensation":[74],"parameters":[75],"minimizing":[77],"error":[79],"between":[80],"real":[81,117],"simulated":[83],"joint":[84],"trajectories.":[85],"These":[86],"calibrated":[87],"dynamics":[88],"are":[89],"then":[90],"used":[91],"train":[93],"TQC-based":[95],"agent":[98],"in":[99,106,125,156],"simulation.":[100],"The":[101],"trained":[102],"policy":[103,129,136],"is":[104],"evaluated":[105],"both":[107],"Gazebo":[108],"MuJoCo":[110],"environments,":[111],"finally":[113],"deployed":[114],"on":[115],"robot.":[118],"Our":[119],"results":[120],"demonstrate":[121],"significant":[123],"improvement":[124],"tracking":[126],"accuracy":[127],"robustness":[130],"after":[131],"tuning,":[133],"smooth":[135],"across":[143],"multiple":[144],"target-reaching":[145],"tasks.":[146],"This":[147],"work":[148],"highlights":[149],"effectiveness":[151],"of":[152],"accurate":[153],"physical":[154],"enabling":[157],"stable":[158],"generalizable":[160],"torque-based":[161],"policies.":[164]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-08-26T00:00:00"}