{"id":"https://openalex.org/W7131857375","doi":"https://doi.org/10.1109/sii64115.2026.11404486","title":"Learning Humanoid Loco-manipulation with Constraints as Terminations","display_name":"Learning Humanoid Loco-manipulation with Constraints as Terminations","publication_year":2026,"publication_date":"2026-01-11","ids":{"openalex":"https://openalex.org/W7131857375","doi":"https://doi.org/10.1109/sii64115.2026.11404486"},"language":"en","primary_location":{"id":"doi:10.1109/sii64115.2026.11404486","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii64115.2026.11404486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-05553678v1/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120749274","display_name":"Pierre-Alexandre Leziart","orcid":null},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Pierre-Alexandre Leziart","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),CNRS-AIST JRL (Joint Robotics Laboratory),Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),CNRS-AIST JRL (Joint Robotics Laboratory),Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014473932","display_name":"Mitsuharu Morisawa","orcid":"https://orcid.org/0000-0003-0056-4335"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mitsuharu Morisawa","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),CNRS-AIST JRL (Joint Robotics Laboratory),Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),CNRS-AIST JRL (Joint Robotics Laboratory),Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091136016","display_name":"Fumio Kanehiro","orcid":"https://orcid.org/0000-0002-0277-3467"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fumio Kanehiro","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),CNRS-AIST JRL (Joint Robotics Laboratory),Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),CNRS-AIST JRL (Joint Robotics Laboratory),Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"325","last_page":"332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.6093000173568726,"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":0.6093000173568726,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.07800000160932541,"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/T12290","display_name":"Human Motion and Animation","score":0.06909999996423721,"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/humanoid-robot","display_name":"Humanoid robot","score":0.6822999715805054},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6754999756813049},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5863000154495239},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5414000153541565},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4869000017642975},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4724000096321106},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3458999991416931}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067000269889832},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.6822999715805054},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6754999756813049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.644599974155426},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5863000154495239},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4869000017642975},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4724000096321106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38019999861717224},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3458999991416931},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34220001101493835},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.3091000020503998},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28940001130104065},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.27300000190734863}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/sii64115.2026.11404486","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii64115.2026.11404486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05553678v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05553678","pdf_url":"https://hal.science/hal-05553678v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"https://sice-si.org/SII2026/","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05553678v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05553678","pdf_url":"https://hal.science/hal-05553678v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"https://sice-si.org/SII2026/","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5269380807876587}],"awards":[{"id":"https://openalex.org/G3499414489","display_name":null,"funder_award_id":"JP22H05002","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7131857375.pdf","grobid_xml":"https://content.openalex.org/works/W7131857375.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2076337359","https://openalex.org/W2158782408","https://openalex.org/W2784449021","https://openalex.org/W2981479926","https://openalex.org/W3015880599","https://openalex.org/W3125490529","https://openalex.org/W3152878473","https://openalex.org/W3170422092","https://openalex.org/W3175254947","https://openalex.org/W3176880374","https://openalex.org/W3204973825","https://openalex.org/W4226250682","https://openalex.org/W4281479885","https://openalex.org/W4283206712","https://openalex.org/W4283787029","https://openalex.org/W4286373058","https://openalex.org/W4293566197","https://openalex.org/W4312574175","https://openalex.org/W4385475819","https://openalex.org/W4386136919","https://openalex.org/W4387197141","https://openalex.org/W4390480962","https://openalex.org/W4391021333","https://openalex.org/W4396243545","https://openalex.org/W4396542455","https://openalex.org/W4396910086","https://openalex.org/W4401414436","https://openalex.org/W4401415103","https://openalex.org/W4401415792","https://openalex.org/W4401415879","https://openalex.org/W4405778675","https://openalex.org/W4405785208","https://openalex.org/W4406779533"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"is":[4,143],"now":[5],"commonly":[6],"used":[7],"for":[8],"controlling":[9],"legged":[10],"robots.":[11],"Several":[12],"recent":[13],"studies":[14],"have":[15],"demonstrated":[16],"impressive":[17],"results":[18],"in":[19,28,108],"solving":[20],"increasingly":[21],"complex":[22],"robotic":[23],"tasks":[24],"such":[25],"as":[26,88],"navigation":[27],"unstructured":[29],"environments":[30],"or":[31,118],"loco-manipulation.":[32],"However,":[33],"this":[34,52],"complexity":[35],"often":[36],"comes":[37],"with":[38,61],"intricate":[39],"learning":[40,105],"setups":[41],"requiring":[42],"tedious":[43],"reward":[44],"shaping":[45],"and":[46,58,111],"features":[47,106],"to":[48,121,128,146,151],"help":[49],"convergence.":[50],"In":[51],"work,":[53],"we":[54,99],"tackle":[55],"these":[56],"issues":[57],"achieve":[59],"loco-manipulation":[60,153],"a":[62,66,152],"humanoid":[63],"robot":[64],"using":[65],"RL":[67],"algorithm":[68],"that":[69,96,113,138],"enforces":[70],"constraints":[71,89],"through":[72],"stochastic":[73],"terminations":[74],"during":[75],"policy":[76],"learning.":[77],"We":[78,135],"keep":[79],"the":[80,101,109,122,139],"number":[81],"of":[82,103],"rewards":[83],"low":[84],"by":[85],"reformulating":[86],"them":[87],"when":[90],"they":[91],"can":[92],"be":[93],"intuitively":[94],"expressed":[95],"way.":[97],"Moreover,":[98],"study":[100],"relevance":[102],"various":[104],"encountered":[107],"literature":[110],"show":[112],"providing":[114],"observations":[115],"without":[116],"noise":[117],"privileged":[119],"information":[120],"critic":[123],"are":[124,159],"two":[125],"straightforward":[126],"ways":[127],"boost":[129],"locomotion":[130,148],"performances":[131],"on":[132],"rough":[133],"terrains.":[134],"also":[136],"demonstrate":[137],"proposed":[140],"minimalist":[141],"architecture":[142],"not":[144],"limited":[145],"pure":[147],"but":[149],"extends":[150],"task":[154],"involving":[155],"upper":[156],"limbs.":[157],"Videos":[158],"available":[160],"at":[161],"humanoid-cat.github.io.":[162]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-28T00:00:00"}