{"id":"https://openalex.org/W4312563990","doi":"https://doi.org/10.1109/iros47612.2022.9982041","title":"Cola-HRL: Continuous-Lattice Hierarchical Reinforcement Learning for Autonomous Driving","display_name":"Cola-HRL: Continuous-Lattice Hierarchical Reinforcement Learning for Autonomous Driving","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312563990","doi":"https://doi.org/10.1109/iros47612.2022.9982041"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9982041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9982041","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5052412385","display_name":"Lingping Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lingping Gao","raw_affiliation_strings":["Alibaba Group,Hangzhou,China,310000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China,310000","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030950316","display_name":"Ziqing Gu","orcid":"https://orcid.org/0000-0003-2990-9632"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqing Gu","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University,State Key Lab of Automotive Safety and Energy,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,State Key Lab of Automotive Safety and Energy,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082153034","display_name":"Cong Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Qiu","raw_affiliation_strings":["Alibaba Group,Hangzhou,China,310000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China,310000","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030969814","display_name":"Lanxin Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanxin Lei","raw_affiliation_strings":["Alibaba Group,Hangzhou,China,310000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China,310000","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747108","display_name":"Shengbo Eben Li","orcid":"https://orcid.org/0000-0003-4923-3633"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University,State Key Lab of Automotive Safety and Energy,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,State Key Lab of Automotive Safety and Energy,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036282981","display_name":"Sifa Zheng","orcid":"https://orcid.org/0000-0001-5160-1365"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sifa Zheng","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University,State Key Lab of Automotive Safety and Energy,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,State Key Lab of Automotive Safety and Energy,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103244741","display_name":"Wei Jing","orcid":"https://orcid.org/0000-0003-3286-5925"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Jing","raw_affiliation_strings":["Alibaba Group,Hangzhou,China,310000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China,310000","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100631549","display_name":"Junbo Chen","orcid":"https://orcid.org/0000-0002-3752-1681"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junbo Chen","raw_affiliation_strings":["Alibaba Group,Hangzhou,China,310000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China,310000","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5052412385"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":3.6263,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.95795602,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"13143","last_page":"13150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.9991000294685364,"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/T10524","display_name":"Traffic control and management","score":0.9972000122070312,"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/reachability","display_name":"Reachability","score":0.8851358890533447},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8253747224807739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.816550612449646},{"id":"https://openalex.org/keywords/cola","display_name":"Cola (plant)","score":0.5206886529922485},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4384080767631531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35651731491088867},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16198429465293884}],"concepts":[{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.8851358890533447},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8253747224807739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816550612449646},{"id":"https://openalex.org/C2781138811","wikidata":"https://www.wikidata.org/wiki/Q114264","display_name":"Cola (plant)","level":2,"score":0.5206886529922485},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4384080767631531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35651731491088867},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16198429465293884},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9982041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9982041","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5149796413","display_name":null,"funder_award_id":"2020AAA0108104","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2062573767","https://openalex.org/W2107338474","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2342840547","https://openalex.org/W2505763307","https://openalex.org/W2583993537","https://openalex.org/W2736601468","https://openalex.org/W2736791111","https://openalex.org/W2758731390","https://openalex.org/W2766447205","https://openalex.org/W2895923634","https://openalex.org/W2897697565","https://openalex.org/W2909906617","https://openalex.org/W2964227312","https://openalex.org/W2968202530","https://openalex.org/W2968983352","https://openalex.org/W2989958156","https://openalex.org/W2990123902","https://openalex.org/W2991419354","https://openalex.org/W2996430598","https://openalex.org/W3002044607","https://openalex.org/W3034722190","https://openalex.org/W3100944043","https://openalex.org/W3130519362","https://openalex.org/W3130665528","https://openalex.org/W3132669183","https://openalex.org/W3137786033","https://openalex.org/W3181452220","https://openalex.org/W3193987867","https://openalex.org/W3205257000","https://openalex.org/W3205367325","https://openalex.org/W3209253128","https://openalex.org/W4200273126","https://openalex.org/W4224216677","https://openalex.org/W4226245271","https://openalex.org/W4234690093","https://openalex.org/W4385245566","https://openalex.org/W6704559304","https://openalex.org/W6739901393","https://openalex.org/W6741002519","https://openalex.org/W6752963931","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2127267268","https://openalex.org/W2136512912","https://openalex.org/W2067910792","https://openalex.org/W2156446763","https://openalex.org/W2150194458","https://openalex.org/W2143461633","https://openalex.org/W2889071233","https://openalex.org/W4321471459","https://openalex.org/W4221156924","https://openalex.org/W2380814829"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3],"shown":[4],"promising":[5],"performance":[6,152],"in":[7,11,102],"autonomous":[8,95],"driving":[9,52,96,154],"applications":[10],"recent":[12],"years.":[13],"The":[14],"early":[15],"end-to-end":[16],"RL":[17,31,91,159],"method":[18,33,93,125,140,148],"is":[19],"usually":[20],"unexplainable":[21],"and":[22,116,122,153],"fails":[23],"to":[24,75,98,110,157],"generate":[25,59,76,111],"stable":[26],"actions,":[27],"while":[28],"the":[29,36,63,83,107],"hierarchical":[30],"(HRL)":[32],"can":[34,141],"tackle":[35],"above":[37,84],"issues":[38],"by":[39],"dividing":[40],"complex":[41],"problems":[42],"into":[43],"multiple":[44,143],"sub-tasks.":[45],"Prior":[46],"HRL":[47],"works":[48],"either":[49],"select":[50],"discrete":[51],"behaviors":[53,155],"with":[54,78],"continuous":[55],"control":[56],"commands,":[57],"or":[58,73],"expected":[60],"goals":[61,77],"for":[62,94],"low-level":[64],"controller.":[65],"However,":[66],"they":[67],"typically":[68],"have":[69],"strong":[70],"scenario":[71],"dependence":[72],"fail":[74],"good":[79],"quality.":[80],"To":[81],"address":[82],"challenges,":[85],"we":[86,120],"propose":[87],"a":[88],"Continuous-Lattice":[89],"Hierarchical":[90],"(Cola-HRL)":[92],"tasks":[97],"make":[99],"high-quality":[100],"decisions":[101],"various":[103],"scenarios.":[104,144],"We":[105],"utilize":[106],"continuous-lattice":[108],"module":[109],"reasonable":[112],"goals,":[113],"ensuring":[114],"temporal":[115],"spatial":[117],"reachability.":[118],"Then,":[119],"train":[121],"evaluate":[123],"our":[124,139,147],"under":[126],"different":[127],"traffic":[128],"scenarios":[129],"based":[130],"on":[131],"real-world":[132],"High":[133],"Definition":[134],"maps.":[135],"Experimental":[136],"results":[137],"show":[138],"handle":[142],"In":[145],"addition,":[146],"also":[149],"demonstrates":[150],"better":[151],"compared":[156],"existing":[158],"methods.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}