{"id":"https://openalex.org/W4413925182","doi":"https://doi.org/10.1109/icra55743.2025.11128867","title":"Hierarchical Reinforcement Learning for Safe Mapless Navigation with Congestion Estimation","display_name":"Hierarchical Reinforcement Learning for Safe Mapless Navigation with Congestion Estimation","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925182","doi":"https://doi.org/10.1109/icra55743.2025.11128867"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5054634605","display_name":"Jianqi Gao","orcid":"https://orcid.org/0000-0003-4486-3740"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianqi Gao","raw_affiliation_strings":["School of Inteligence Science and Engineering, Harbin Institute of Technology,Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics,Department of Guangdong,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"School of Inteligence Science and Engineering, Harbin Institute of Technology,Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics,Department of Guangdong,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047707212","display_name":"Xizheng Pang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xizheng Pang","raw_affiliation_strings":["School of Inteligence Science and Engineering, Harbin Institute of Technology,Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics,Department of Guangdong,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"School of Inteligence Science and Engineering, Harbin Institute of Technology,Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics,Department of Guangdong,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453159","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0001-7485-6344"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Liu","raw_affiliation_strings":["Northeastern University,Faculty of Robot Science and Engineering,Shenyang,China,110819"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Faculty of Robot Science and Engineering,Shenyang,China,110819","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100677181","display_name":"Yanjie Li","orcid":"https://orcid.org/0000-0002-4074-5109"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjie Li","raw_affiliation_strings":["School of Inteligence Science and Engineering, Harbin Institute of Technology,Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics,Department of Guangdong,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"School of Inteligence Science and Engineering, Harbin Institute of Technology,Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics,Department of Guangdong,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054634605"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":3.1134,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92985906,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8849","last_page":"8855"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10080","display_name":"Energy Efficient Wireless Sensor Networks","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10080","display_name":"Energy Efficient Wireless Sensor Networks","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9778000116348267,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9764000177383423,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.8531373739242554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6972547173500061},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4750135838985443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41724854707717896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33350515365600586},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16154241561889648}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8531373739242554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6972547173500061},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4750135838985443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41724854707717896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33350515365600586},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16154241561889648},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2055181353","display_name":null,"funder_award_id":"61977019,U1813206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4816949318","display_name":null,"funder_award_id":"JCYJ20220818102415033,JSGG20201103093802006,KJZD20230923114222045","funder_id":"https://openalex.org/F4320329791","funder_display_name":"Shenzhen Fundamental Research Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2157331557","https://openalex.org/W2167052694","https://openalex.org/W2746553466","https://openalex.org/W3195968524","https://openalex.org/W3206901743","https://openalex.org/W4316669314","https://openalex.org/W4321783814","https://openalex.org/W4324119411","https://openalex.org/W4368232707","https://openalex.org/W4376891105","https://openalex.org/W4379801785","https://openalex.org/W4386634158","https://openalex.org/W4386820640","https://openalex.org/W4391422753","https://openalex.org/W4399030928"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Reinforcement":[0],"learning-based":[1],"mapless":[2,23],"navigation":[3,24,33,46,121,138,152],"holds":[4],"significant":[5],"potential.":[6],"However,":[7],"it":[8],"faces":[9],"challenges":[10],"in":[11,67,126,141],"indoor":[12],"environments":[13],"with":[14],"local":[15,68],"minima":[16],"area.":[17],"This":[18],"paper":[19],"introduces":[20],"a":[21,41,52,98,155],"safe":[22,78],"framework":[25,139,153],"utilizing":[26],"hierarchical":[27],"reinforcement":[28,79],"learning":[29],"(HRL)":[30],"to":[31,43,90],"enhance":[32,91],"through":[34,77],"such":[35],"areas.":[36,70],"The":[37,71,132],"high-level":[38],"policy":[39],"creates":[40],"sub-goal":[42,53],"direct":[44],"the":[45,62,65,92,105,110,116,150],"process.":[47],"Notably,":[48],"we":[49,96,123,148],"have":[50],"developed":[51],"update":[54],"mechanism":[55],"that":[56,103,135],"considers":[57],"environment":[58],"congestion,":[59],"efficiently":[60],"avoiding":[61],"entrapment":[63],"of":[64,107,118],"robot":[66,157],"minimum":[69],"low-level":[72],"motion":[73,112],"planning":[74],"policy,":[75],"trained":[76],"learning,":[80],"outputs":[81],"real-time":[82],"control":[83],"instructions":[84],"based":[85],"on":[86,109,154],"acquired":[87],"sub-goal.":[88],"Specifically,":[89],"robot's":[93,111],"environmental":[94],"perception,":[95],"introduce":[97],"new":[99],"obstacle":[100],"encoding":[101],"method":[102],"evaluates":[104],"impact":[106],"obstacles":[108],"planning.":[113],"To":[114],"validate":[115],"performance":[117],"our":[119,136],"HRL-based":[120,137,151],"framework,":[122],"conduct":[124],"simulations":[125],"office,":[127],"home,":[128],"and":[129,144],"restaurant":[130],"environments.":[131],"findings":[133],"demonstrate":[134],"excels":[140],"both":[142],"static":[143],"dynamic":[145],"scenarios.":[146],"Finally,":[147],"implement":[149],"TurtleBot3":[156],"for":[158],"validation":[159],"experiments,":[160],"which":[161],"exhibits":[162],"its":[163],"strong":[164],"generalization":[165],"capabilities.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}