{"id":"https://openalex.org/W4401417117","doi":"https://doi.org/10.1109/icra57147.2024.10610668","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":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401417117","doi":"https://doi.org/10.1109/icra57147.2024.10610668"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5108854600","display_name":"Zifan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zifan Xu","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006997685","display_name":"Amir Hossain Raj","orcid":"https://orcid.org/0009-0007-7889-6352"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amir Hossain Raj","raw_affiliation_strings":["George Mason University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Mason University","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017662025","display_name":"Xuesu Xiao","orcid":"https://orcid.org/0000-0001-5151-2186"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuesu Xiao","raw_affiliation_strings":["George Mason University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Mason University","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001594330","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0002-6795-420X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Stone","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11474","last_page":"11480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9995999932289124,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9939000010490417,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.792831301689148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6097045540809631},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4796757698059082},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4711132347583771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.334270179271698},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20749622583389282},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.0711500346660614}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.792831301689148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6097045540809631},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4796757698059082},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4711132347583771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.334270179271698},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20749622583389282},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0711500346660614}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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":36,"referenced_works":["https://openalex.org/W1584018316","https://openalex.org/W1975230295","https://openalex.org/W2081469022","https://openalex.org/W2094496385","https://openalex.org/W2099428832","https://openalex.org/W2161427949","https://openalex.org/W2162768030","https://openalex.org/W2345626358","https://openalex.org/W2694031977","https://openalex.org/W2736601468","https://openalex.org/W2901522995","https://openalex.org/W2911087563","https://openalex.org/W2938249325","https://openalex.org/W2963184939","https://openalex.org/W2964339842","https://openalex.org/W2968213087","https://openalex.org/W3013410780","https://openalex.org/W3034811151","https://openalex.org/W3090443808","https://openalex.org/W3134580056","https://openalex.org/W3155009074","https://openalex.org/W3175254947","https://openalex.org/W3209211683","https://openalex.org/W4206589784","https://openalex.org/W4250058668","https://openalex.org/W4283787029","https://openalex.org/W4283788634","https://openalex.org/W4285102283","https://openalex.org/W4311486620","https://openalex.org/W4312574175","https://openalex.org/W4313196885","https://openalex.org/W6741002519","https://openalex.org/W6765121789","https://openalex.org/W6802654813","https://openalex.org/W6846664724","https://openalex.org/W6847063038"],"related_works":["https://openalex.org/W4391375266","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"],"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":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}