{"id":"https://openalex.org/W4416748773","doi":"https://doi.org/10.1109/iros60139.2025.11246602","title":"Preferenced Oracle Guided Multi-mode Policies for Dynamic Bipedal Loco-Manipulation","display_name":"Preferenced Oracle Guided Multi-mode Policies for Dynamic Bipedal Loco-Manipulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748773","doi":"https://doi.org/10.1109/iros60139.2025.11246602"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5114452460","display_name":"Prashanth Ravichandar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Prashanth Ravichandar","raw_affiliation_strings":["Dynamic Robotics and Control Laboratory, University of Southern California,Los Angeles,USA,CA 90089"],"affiliations":[{"raw_affiliation_string":"Dynamic Robotics and Control Laboratory, University of Southern California,Los Angeles,USA,CA 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071232916","display_name":"Lokesh Krishna","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lokesh Krishna","raw_affiliation_strings":["Dynamic Robotics and Control Laboratory, University of Southern California,Los Angeles,USA,CA 90089"],"affiliations":[{"raw_affiliation_string":"Dynamic Robotics and Control Laboratory, University of Southern California,Los Angeles,USA,CA 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094105682","display_name":"Nikhil Sobanbabu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikhil Sobanbabu","raw_affiliation_strings":["Dynamic Robotics and Control Laboratory, University of Southern California,Los Angeles,USA,CA 90089"],"affiliations":[{"raw_affiliation_string":"Dynamic Robotics and Control Laboratory, University of Southern California,Los Angeles,USA,CA 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210116723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091022089","display_name":"Quan Dong Nguyen","orcid":"https://orcid.org/0000-0002-6024-8441"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quan Nguyen","raw_affiliation_strings":["Dynamic Robotics and Control Laboratory, University of Southern California,Los Angeles,USA,CA 90089"],"affiliations":[{"raw_affiliation_string":"Dynamic Robotics and Control Laboratory, University of Southern California,Los Angeles,USA,CA 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210116723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114452460"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210116723"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48212286,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6600","last_page":"6606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5250999927520752,"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":0.5250999927520752,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.23420000076293945,"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/T10982","display_name":"Motor Control and Adaptation","score":0.07109999656677246,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.7501000165939331},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.611299991607666},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5329999923706055},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49720001220703125},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.45010000467300415},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.44209998846054077},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.4377000033855438},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43479999899864197}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7501000165939331},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.611299991607666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5741000175476074},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5329999923706055},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49720001220703125},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4320000112056732},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3310999870300293},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.31119999289512634},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26249998807907104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1975236902","https://openalex.org/W2147340401","https://openalex.org/W2788030459","https://openalex.org/W2911087563","https://openalex.org/W2951360122","https://openalex.org/W2963184939","https://openalex.org/W3039737909","https://openalex.org/W3089467114","https://openalex.org/W3093922502","https://openalex.org/W3123076862","https://openalex.org/W3176539729","https://openalex.org/W4205430897","https://openalex.org/W4367016688","https://openalex.org/W4382935639","https://openalex.org/W4383108493","https://openalex.org/W4385858056","https://openalex.org/W4388895019","https://openalex.org/W4388901983","https://openalex.org/W4389665855","https://openalex.org/W4389667244","https://openalex.org/W4390494915","https://openalex.org/W4394674699","https://openalex.org/W4394872716","https://openalex.org/W4401414436","https://openalex.org/W4401415792","https://openalex.org/W4403741606","https://openalex.org/W4413925046"],"related_works":[],"abstract_inverted_index":{"Dynamic":[0],"loco-manipulation":[1,103,153,195],"calls":[2],"for":[3,154],"effective":[4],"whole-body":[5,163],"control":[6,18],"and":[7,13,26,65,95,117,158,180,185,209,216],"contact-rich":[8,178],"interactions":[9],"with":[10,29,114,199],"the":[11,14,51,56,92,174,189,212],"object":[12],"environment.":[15],"Existing":[16],"learning-based":[17],"synthesis":[19],"relies":[20],"on":[21,197],"training":[22],"low-level":[23],"skill":[24],"policies":[25],"explicitly":[27],"switching":[28],"a":[30,34,68,87,123,133,141,167],"high-level":[31],"policy":[32,89,125,169],"or":[33],"hand-designed":[35],"finite":[36],"state":[37],"machine,":[38],"leading":[39],"to":[40,53,59,63,85,100,111,121,171,177],"quasi-static":[41],"behaviors.":[42],"In":[43,165],"contrast,":[44],"dynamic":[45],"tasks":[46,155],"such":[47],"as":[48,109],"soccer":[49,157],"require":[50],"robot":[52],"run":[54],"towards":[55],"ball,":[57,175],"decelerate":[58],"an":[60],"optimal":[61],"approach":[62,150],"dribble,":[64],"eventually":[66],"kick":[67],"goal\u2014a":[69],"continuum":[70],"of":[71,98,136],"smooth":[72],"motion.":[73],"To":[74,130],"this":[75],"end,":[76],"we":[77,139,192],"propose":[78],"Preferenced":[79],"Oracle":[80],"Guided":[81],"Multi-mode":[82],"Policies":[83],"(OGMP)":[84],"learn":[86],"single":[88,168],"mastering":[90],"all":[91],"required":[93],"modes":[94],"preferred":[96],"sequence":[97,135],"transitions":[99],"solve":[101,193],"uni-object":[102],"tasks.":[104],"We":[105],"design":[106],"hybrid":[107],"automatons":[108],"oracles":[110],"generate":[112],"references":[113],"continuous":[115],"dynamics":[116],"discrete":[118],"mode":[119,137],"jumps":[120],"perform":[122],"guided":[124],"optimization":[126],"through":[127,162],"bounded":[128],"exploration.":[129],"enforce":[131],"learning":[132],"desired":[134],"transitions,":[138],"present":[140],"task-agnostic":[142],"preference":[143],"reward":[144,214],"that":[145],"enhances":[146],"performance.":[147],"The":[148],"proposed":[149],"demonstrates":[151],"successful":[152,182],"like":[156],"moving":[159],"boxes":[160],"omnidirectionally":[161],"control.":[164],"soccer,":[166],"learns":[170],"optimally":[172],"reach":[173],"transition":[176],"dribbling,":[179],"execute":[181],"goal":[183],"kicks":[184],"ball":[186],"stops.":[187],"Leveraging":[188],"oracle\u2019s":[190],"abstraction,":[191],"each":[194],"task":[196],"robots":[198],"varying":[200],"morphologies,":[201],"including":[202],"HECTOR":[203],"V1,":[204],"Berkeley":[205],"Humanoid,":[206],"Unitree":[207],"G1,":[208],"H1,":[210],"using":[211],"same":[213],"definition":[215],"weights.":[217]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}