{"id":"https://openalex.org/W4413925876","doi":"https://doi.org/10.1109/icra55743.2025.11127448","title":"Residual Policy Learning for Perceptive Quadruped Control Using Differentiable Simulation","display_name":"Residual Policy Learning for Perceptive Quadruped Control Using Differentiable Simulation","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925876","doi":"https://doi.org/10.1109/icra55743.2025.11127448"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5113336001","display_name":"Jing Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Jing Yuan Luo","raw_affiliation_strings":["ETH Zurich,Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085971429","display_name":"Yunlong Song","orcid":"https://orcid.org/0000-0002-6352-3744"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yunlong Song","raw_affiliation_strings":["University of Zurich,Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Zurich,Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041410798","display_name":"Victor Klemm","orcid":"https://orcid.org/0000-0002-6752-3397"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Victor Klemm","raw_affiliation_strings":["ETH Zurich,Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043420881","display_name":"Fan Shi","orcid":"https://orcid.org/0000-0002-9202-1727"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fan Shi","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057116316","display_name":"Davide Scaramuzza","orcid":"https://orcid.org/0000-0002-3831-6778"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Davide Scaramuzza","raw_affiliation_strings":["University of Zurich,Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Zurich,Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044258783","display_name":"Marco Hutter","orcid":"https://orcid.org/0000-0002-4285-4990"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marco Hutter","raw_affiliation_strings":["ETH Zurich,Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5113336001"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":5.2738,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95848391,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11749","display_name":"Iterative Learning Control Systems","score":0.5515000224113464,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.5515000224113464,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.4797999858856201,"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/residual","display_name":"Residual","score":0.7983707189559937},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.758141279220581},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5965238213539124},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4920591711997986},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4863322377204895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3561527132987976},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.35078680515289307},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22158744931221008},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1321485936641693},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12874683737754822}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7983707189559937},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.758141279220581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5965238213539124},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4920591711997986},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4863322377204895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3561527132987976},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.35078680515289307},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22158744931221008},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1321485936641693},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12874683737754822},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W4386718967","https://openalex.org/W4390938336","https://openalex.org/W4402354032","https://openalex.org/W4402354142"],"related_works":["https://openalex.org/W4285277090","https://openalex.org/W4327738859","https://openalex.org/W2348722996","https://openalex.org/W2334570605","https://openalex.org/W3181683615","https://openalex.org/W4286826125","https://openalex.org/W1633485514","https://openalex.org/W1604739066","https://openalex.org/W2115878407","https://openalex.org/W2560215812"],"abstract_inverted_index":{"First-order":[0],"Policy":[1,12],"Gradient":[2],"(FoPG)":[3],"algorithms":[4,37],"such":[5],"as":[6],"Backpropagation":[7],"through":[8],"Time":[9],"and":[10,143],"Analytical":[11],"Gradients":[13],"leverage":[14],"local":[15,119],"simulation":[16,60],"physics":[17],"to":[18,30,98,103,117,125,140],"accelerate":[19],"policy":[20,68,89],"search,":[21],"significantly":[22],"improving":[23,104],"sample":[24,105],"efficiency":[25,106],"in":[26,43,91,150],"robot":[27,124],"control":[28],"compared":[29,102],"standard":[31],"model-free":[32,108],"reinforcement":[33],"learning.":[34],"However,":[35],"FoPG":[36,135],"can":[38],"exhibit":[39],"poor":[40],"learning":[41,71,90],"dynamics":[42,56],"contact-rich":[44],"tasks":[45],"like":[46],"locomotion.":[47],"Previous":[48],"approaches":[49],"address":[50],"this":[51],"issue":[52],"by":[53,70,137],"alleviating":[54],"contact":[55],"via":[57],"algorithmic":[58],"or":[59],"innovations.":[61],"In":[62],"contrast,":[63],"we":[64,82,111,130],"propose":[65],"guiding":[66],"the":[67,85,132],"search":[69],"a":[72,75,122,148],"residual":[73,88],"over":[74],"simple":[76],"baseline":[77],"policy.":[78],"For":[79],"quadruped":[80,149],"locomotion,":[81],"find":[83],"that":[84],"role":[86],"of":[87,134],"FoPG-based":[92],"training":[93,121],"(FoPG":[94],"RPL)":[95],"is":[96],"primarily":[97],"improve":[99],"asymptotic":[100],"rewards,":[101],"for":[107],"RL.":[109],"Additionally,":[110],"provide":[112],"insights":[113],"on":[114,147],"applying":[115],"FoPG's":[116],"pixel-based":[118],"navigation,":[120],"point-mass":[123],"convergence":[126],"within":[127],"seconds.":[128],"Finally,":[129],"showcase":[131],"versatility":[133],"RPL":[136],"using":[138],"it":[139],"train":[141],"locomotion":[142],"perceptive":[144],"navigation":[145],"end-toend":[146],"minutes.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}
