{"id":"https://openalex.org/W4392576560","doi":"https://doi.org/10.48550/arxiv.2403.03848","title":"Dexterous Legged Locomotion in Confined 3D Spaces with Reinforcement Learning","display_name":"Dexterous Legged Locomotion in Confined 3D Spaces with Reinforcement Learning","publication_year":2024,"publication_date":"2024-03-06","ids":{"openalex":"https://openalex.org/W4392576560","doi":"https://doi.org/10.48550/arxiv.2403.03848"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.03848","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03848","pdf_url":"https://arxiv.org/pdf/2403.03848","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.03848","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108854600","display_name":"Zifan Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xu, Zifan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006997685","display_name":"Amir Hossain Raj","orcid":"https://orcid.org/0009-0007-7889-6352"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raj, Amir Hossain","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017662025","display_name":"Xuesu Xiao","orcid":"https://orcid.org/0000-0001-5151-2186"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Xuesu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001594330","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0002-6795-420X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stone, Peter","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108854600"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9377999901771545,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9377999901771545,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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":0.9194999933242798,"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/T13518","display_name":"Architecture and Computational Design","score":0.9092000126838684,"subfield":{"id":"https://openalex.org/subfields/2216","display_name":"Architecture"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7001245021820068},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6251786947250366},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44641104340553284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27796825766563416},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.25074252486228943},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.11587733030319214}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7001245021820068},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6251786947250366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44641104340553284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27796825766563416},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25074252486228943},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.11587733030319214}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.03848","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03848","pdf_url":"https://arxiv.org/pdf/2403.03848","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.03848","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.03848","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.03848","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03848","pdf_url":"https://arxiv.org/pdf/2403.03848","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392576560.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"of":[2,16,131,231],"locomotion":[3,21,78,117,140,181,222],"controllers":[4,37],"utilizing":[5],"deep":[6],"reinforcement":[7],"learning":[8,218],"(RL)":[9],"have":[10],"yielded":[11],"impressive":[12],"results":[13],"in":[14,123],"terms":[15],"achieving":[17],"rapid":[18],"and":[19,31,87,108,158,188,220],"robust":[20,109],"across":[22],"challenging":[23,98],"terrain,":[24],"such":[25,55,84],"as":[26,56,85],"rugged":[27],"rocks,":[28],"non-rigid":[29],"ground,":[30],"slippery":[32],"surfaces.":[33],"However,":[34],"while":[35],"these":[36,165],"primarily":[38],"address":[39,128],"challenges":[40],"underneath":[41],"the":[42,129,175,184,227],"robot,":[43],"relatively":[44],"little":[45],"research":[46],"has":[47],"investigated":[48],"legged":[49,110],"mobility":[50],"through":[51,97,209],"confined":[52,99,124,211],"3D":[53,100,105,125,212],"spaces,":[54,101],"narrow":[57],"tunnels":[58],"or":[59],"irregular":[60],"voids,":[61],"which":[62],"impose":[63],"all-around":[64],"constraints.":[65],"The":[66],"cyclic":[67],"gait":[68],"patterns":[69],"resulted":[70],"from":[71,120],"existing":[72],"RL-based":[73,160],"methods":[74],"to":[75,94,115,151,163,177],"learn":[76,116],"parameterized":[77,221],"skills":[79,118,182],"characterized":[80],"by":[81,167],"motion":[82,170],"parameters,":[83],"velocity":[86],"body":[88],"height,":[89],"may":[90],"not":[91],"be":[92],"adequate":[93],"navigate":[95],"robots":[96],"requiring":[102],"both":[103,215],"agile":[104],"obstacle":[106],"avoidance":[107],"locomotion.":[111],"Instead,":[112],"we":[113,136],"propose":[114],"end-to-end":[119,217],"goal-oriented":[121],"navigation":[122,134,197],"spaces.":[126],"To":[127],"inefficiency":[130],"tracking":[132],"distant":[133,199],"goals,":[135,194],"introduce":[137],"a":[138,144,153,236],"hierarchical":[139,204],"controller":[141,234],"that":[142],"combines":[143],"classical":[145],"planner":[146],"tasked":[147],"with":[148],"planning":[149],"waypoints":[150,166],"reach":[152],"faraway":[154],"global":[155],"goal":[156],"location,":[157],"an":[159],"policy":[161,176],"trained":[162],"follow":[164],"generating":[168],"low-level":[169],"commands.":[171],"This":[172],"approach":[173,205],"allows":[174],"explore":[178],"its":[179],"own":[180],"within":[183],"entire":[185],"solution":[186],"space":[187],"facilitates":[189],"smooth":[190],"transitions":[191],"between":[192],"local":[193],"enabling":[195],"long-term":[196],"towards":[198],"goals.":[200],"In":[201],"simulation,":[202],"our":[203,232],"succeeds":[206],"at":[207],"navigating":[208],"demanding":[210],"environments,":[213],"outperforming":[214],"pure":[216],"approaches":[219],"skills.":[223],"We":[224],"further":[225],"demonstrate":[226],"successful":[228],"real-world":[229],"deployment":[230],"simulation-trained":[233],"on":[235],"real":[237],"robot.":[238]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2024-03-08T00:00:00"}