{"id":"https://openalex.org/W4383108450","doi":"https://doi.org/10.1109/icra48891.2023.10160583","title":"Benchmarking Reinforcement Learning Techniques for Autonomous Navigation","display_name":"Benchmarking Reinforcement Learning Techniques for Autonomous Navigation","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108450","doi":"https://doi.org/10.1109/icra48891.2023.10160583"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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":["University of Texas at Austin,Department of Computer Science","Department of Computer Science, University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Department of Computer Science","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111058004","display_name":"Bo Liu","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":"Bo Liu","raw_affiliation_strings":["University of Texas at Austin,Department of Computer Science","Department of Computer Science, University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Department of Computer Science","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"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,Department of Computer Science","Everyday Robots","Department of Computer Science, George Mason University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Mason University,Department of Computer Science","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"Everyday Robots","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, George Mason University","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013037940","display_name":"Anirudh Nair","orcid":"https://orcid.org/0000-0001-7662-7668"},"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":"Anirudh Nair","raw_affiliation_strings":["University of Texas at Austin,Department of Computer Science","Department of Computer Science, University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Department of Computer Science","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"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/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]},{"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":["University of Texas at Austin,Department of Computer Science","Department of Computer Science, University of Texas at Austin","Sony AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Department of Computer Science","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9224","last_page":"9230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998000264167786,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9988999962806702,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.837200939655304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7666082382202148},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6772864460945129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6627817749977112},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6032685041427612},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5559808015823364},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.47453153133392334},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4662420153617859},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4656909704208374},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4290653467178345},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4191010892391205},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.37671518325805664}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.837200939655304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7666082382202148},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6772864460945129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6627817749977112},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6032685041427612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5559808015823364},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.47453153133392334},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4662420153617859},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4656909704208374},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4290653467178345},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4191010892391205},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.37671518325805664},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G347654907","display_name":null,"funder_award_id":"CPS-1739964,IIS-1724157,NRI-1925082","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1662842982","https://openalex.org/W1980035368","https://openalex.org/W1995938954","https://openalex.org/W2117211893","https://openalex.org/W2121092017","https://openalex.org/W2150468603","https://openalex.org/W2152536965","https://openalex.org/W2158782408","https://openalex.org/W2167340365","https://openalex.org/W2605102758","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2891790128","https://openalex.org/W2912063360","https://openalex.org/W2913300629","https://openalex.org/W2962872206","https://openalex.org/W2962887844","https://openalex.org/W2963864421","https://openalex.org/W2976046470","https://openalex.org/W2994073215","https://openalex.org/W2998903229","https://openalex.org/W3004375689","https://openalex.org/W3036170014","https://openalex.org/W3163454111","https://openalex.org/W3190038566","https://openalex.org/W3206314692","https://openalex.org/W3207060053","https://openalex.org/W4220840735","https://openalex.org/W4221161274","https://openalex.org/W4292945781","https://openalex.org/W4297789758","https://openalex.org/W4298206671","https://openalex.org/W6677939520","https://openalex.org/W6684921986","https://openalex.org/W6747473740","https://openalex.org/W6751494529","https://openalex.org/W6754521519","https://openalex.org/W6756840741","https://openalex.org/W6758924645","https://openalex.org/W6771750343","https://openalex.org/W6842721916"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W3134526803","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2643884694","https://openalex.org/W2165180011","https://openalex.org/W4220829754","https://openalex.org/W3165944253","https://openalex.org/W2351343564"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,29,50,66,80,90,98,126,146,179],"(RL)":[3],"has":[4],"brought":[5],"many":[6],"successes":[7],"for":[8,69,75,84,89,100,116,208],"autonomous":[9,70,101,117],"robot":[10],"navigation.":[11,102],"However,":[12],"there":[13],"still":[14],"exists":[15],"important":[16],"limitations":[17],"that":[18],"prevent":[19],"real-world":[20,189],"use":[21,83],"of":[22,48,60,96,111,145,151,156],"RL-based":[23,209],"navigation":[24,36,71,186,210],"systems.":[25,211],"For":[26],"example,":[27],"most":[28],"approaches":[30,115],"lack":[31,59],"safety":[32],"guarantees;":[33],"and":[34,64,88,131,136,172,188],"learned":[35],"systems":[37],"may":[38],"not":[39],"generalize":[40],"well":[41],"to":[42,52,77,82,92,134,199],"unseen":[43],"environments.":[44,138],"Despite":[45],"a":[46,58,182,193],"variety":[47],"recent":[49],"techniques":[51,147,180,204],"tackle":[53],"these":[54,178,203,206],"challenges":[55],"in":[56,181],"general,":[57],"an":[61],"open-source":[62,184],"benchmark":[63,187],"reproducible":[65],"methods":[67,81,99],"specifically":[68],"makes":[72],"it":[73],"difficult":[74],"roboticists":[76],"choose":[78],"what":[79,200],"their":[85],"mobile":[86],"robots":[87],"researchers":[91],"identify":[93,107],"current":[94],"shortcomings":[95],"general":[97],"In":[103],"this":[104],"paper,":[105],"we":[106,140,191],"four":[108,142,158],"major":[109,143],"desiderata":[110,207],"applying":[112],"deep":[113],"RL":[114,166,169],"navigation:":[118],"(D1)":[119],"reasoning":[120],"under":[121],"uncertainty,":[122],"(D2)":[123],"safety,":[124],"(D3)":[125],"from":[127],"limited":[128],"trial-and-error":[129],"data,":[130],"(D4)":[132],"generalization":[133],"diverse":[135],"novel":[137],"Then,":[139],"explore":[141],"classes":[144],"with":[148],"the":[149,157],"purpose":[150],"achieving":[152],"one":[153],"or":[154],"more":[155],"desiderata:":[159],"memory-based":[160],"neural":[161],"network":[162],"architectures":[163],"(D1),":[164],"safe":[165],"(D2),":[167],"model-based":[168],"(D2,":[170],"D3),":[171],"domain":[173],"randomization":[174],"(D4).":[175],"By":[176],"deploying":[177],"new":[183],"large-scale":[185],"environments,":[190],"perform":[192],"comprehensive":[194],"study":[195],"aimed":[196],"at":[197],"establishing":[198],"extent":[201],"can":[202],"achieve":[205]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}