{"id":"https://openalex.org/W3199192745","doi":"https://doi.org/10.1109/icra48506.2021.9561151","title":"Hierarchies of Planning and Reinforcement Learning for Robot Navigation","display_name":"Hierarchies of Planning and Reinforcement Learning for Robot Navigation","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3199192745","doi":"https://doi.org/10.1109/icra48506.2021.9561151","mag":"3199192745"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561151","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.11178","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004987095","display_name":"Jan W\u00f6hlke","orcid":"https://orcid.org/0000-0003-4702-1768"},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]},{"id":"https://openalex.org/I4210145457","display_name":"Robert Bosch (Taiwan)","ror":"https://ror.org/046as2g47","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210145457","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["DE","NL","TW"],"is_corresponding":true,"raw_author_name":"Jan Wohlke","raw_affiliation_strings":["Bosch Center for Artificial Intelligence, Renningen, Germany","UvA-Bosch Delta Lab, University of Amsterdam, Amsterdam, Netherlands","Robert Bosch GmBH"],"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence, Renningen, Germany","institution_ids":["https://openalex.org/I889804353"]},{"raw_affiliation_string":"UvA-Bosch Delta Lab, University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"Robert Bosch GmBH","institution_ids":["https://openalex.org/I4210145457"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030224453","display_name":"Felix Schmitt","orcid":"https://orcid.org/0000-0001-5451-8233"},"institutions":[{"id":"https://openalex.org/I4210145457","display_name":"Robert Bosch (Taiwan)","ror":"https://ror.org/046as2g47","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210145457","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE","TW"],"is_corresponding":false,"raw_author_name":"Felix Schmitt","raw_affiliation_strings":["Bosch Center for Artificial Intelligence, Renningen, Germany","Robert Bosch GmBH"],"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence, Renningen, Germany","institution_ids":["https://openalex.org/I889804353"]},{"raw_affiliation_string":"Robert Bosch GmBH","institution_ids":["https://openalex.org/I4210145457"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057277609","display_name":"Herke van Hoof","orcid":"https://orcid.org/0000-0002-1583-3692"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Herke van Hoof","raw_affiliation_strings":["UvA-Bosch Delta Lab, University of Amsterdam, Amsterdam, Netherlands","University of Amsterdam"],"affiliations":[{"raw_affiliation_string":"UvA-Bosch Delta Lab, University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004987095"],"corresponding_institution_ids":["https://openalex.org/I4210145457","https://openalex.org/I887064364","https://openalex.org/I889804353"],"apc_list":null,"apc_paid":null,"fwci":0.28220715,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63474865,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"10682","last_page":"10688"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9994999766349792,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9089847803115845},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.7615935802459717},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.71197509765625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6904581785202026},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.6166698336601257},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6061570048332214},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.593043863773346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5836759209632874},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.47857239842414856},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.4682914614677429},{"id":"https://openalex.org/keywords/holonomic","display_name":"Holonomic","score":0.4579949975013733},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4546833038330078},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.41907715797424316},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37319695949554443},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.356812983751297},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.12980809807777405},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12769073247909546},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09055647253990173},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.07439830899238586}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9089847803115845},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.7615935802459717},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.71197509765625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6904581785202026},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.6166698336601257},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6061570048332214},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.593043863773346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5836759209632874},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.47857239842414856},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.4682914614677429},{"id":"https://openalex.org/C2777964439","wikidata":"https://www.wikidata.org/wiki/Q5884201","display_name":"Holonomic","level":2,"score":0.4579949975013733},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4546833038330078},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.41907715797424316},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37319695949554443},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.356812983751297},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.12980809807777405},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12769073247909546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09055647253990173},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.07439830899238586},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icra48506.2021.9561151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561151","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2109.11178","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.11178","pdf_url":"https://arxiv.org/pdf/2109.11178","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/600426c6-6a65-4820-9bac-e86e6f4fa4d7","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/hierarchies-of-planning-and-reinforcement-learning-for-robot-navigation(600426c6-6a65-4820-9bac-e86e6f4fa4d7).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA 2021): May 31-June 4, 2021, Xi'an, China, 10682 - 10688","raw_type":"info:eu-repo/semantics/conferencepaper"},{"id":"doi:10.48550/arxiv.2109.11178","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2109.11178","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-journal"},{"id":"mag:3199192745","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.11178","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.11178","pdf_url":"https://arxiv.org/pdf/2109.11178","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1771410628","https://openalex.org/W2097146511","https://openalex.org/W2109910161","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2160371091","https://openalex.org/W2593841437","https://openalex.org/W2594829461","https://openalex.org/W2624142409","https://openalex.org/W2783130291","https://openalex.org/W2795756076","https://openalex.org/W2803281228","https://openalex.org/W2811111819","https://openalex.org/W2883471708","https://openalex.org/W2894605519","https://openalex.org/W2899455150","https://openalex.org/W2902907165","https://openalex.org/W2920215304","https://openalex.org/W2944895446","https://openalex.org/W2946532629","https://openalex.org/W2951660448","https://openalex.org/W2954142106","https://openalex.org/W2958112174","https://openalex.org/W2962712652","https://openalex.org/W2962839548","https://openalex.org/W2962917939","https://openalex.org/W2963072115","https://openalex.org/W2963184621","https://openalex.org/W2963311874","https://openalex.org/W2963523627","https://openalex.org/W2963645756","https://openalex.org/W2963661429","https://openalex.org/W2963938771","https://openalex.org/W2964077562","https://openalex.org/W2964161785","https://openalex.org/W2964220198","https://openalex.org/W2964227312","https://openalex.org/W2964238766","https://openalex.org/W2966130410","https://openalex.org/W2970720334","https://openalex.org/W2993149128","https://openalex.org/W3008165446","https://openalex.org/W3016507688","https://openalex.org/W3029221344","https://openalex.org/W3037007134","https://openalex.org/W3037760466","https://openalex.org/W6604509089","https://openalex.org/W6627932998","https://openalex.org/W6678300755","https://openalex.org/W6682849425","https://openalex.org/W6683821272","https://openalex.org/W6692405165","https://openalex.org/W6695011786","https://openalex.org/W6734215269","https://openalex.org/W6740801417","https://openalex.org/W6740836278","https://openalex.org/W6741302124","https://openalex.org/W6747607884","https://openalex.org/W6748271565","https://openalex.org/W6748594472","https://openalex.org/W6748839928","https://openalex.org/W6752089545","https://openalex.org/W6753611882","https://openalex.org/W6764173040"],"related_works":["https://openalex.org/W2263273879","https://openalex.org/W3146696145","https://openalex.org/W2963129648","https://openalex.org/W3034563340","https://openalex.org/W3096918561","https://openalex.org/W2963572779","https://openalex.org/W3185291728","https://openalex.org/W2513584761","https://openalex.org/W3209810506","https://openalex.org/W3097282424","https://openalex.org/W2224248205","https://openalex.org/W141896198","https://openalex.org/W2760799532","https://openalex.org/W3080156643","https://openalex.org/W3175128928","https://openalex.org/W2986925736","https://openalex.org/W3093210414","https://openalex.org/W3034927287","https://openalex.org/W3196831457","https://openalex.org/W3135457936"],"abstract_inverted_index":{"Solving":[0],"robotic":[1,138],"navigation":[2,23,139],"tasks":[3],"via":[4],"reinforcement":[5],"learning":[6,41],"(RL)":[7],"is":[8,150,168],"challenging":[9],"due":[10],"to":[11,60,164],"their":[12],"sparse":[13],"reward":[14],"and":[15,53,77,110,167],"long":[16],"decision":[17],"horizon":[18],"nature.":[19],"However,":[20,69],"in":[21,49,65,143],"many":[22],"tasks,":[24,140],"high-level":[25],"(HL)":[26],"task":[27,181],"representations,":[28],"like":[29],"a":[30,93,99,123,131,179],"rough":[31],"floor":[32],"plan,":[33],"are":[34],"available.":[35],"Previous":[36],"work":[37,87],"has":[38],"demonstrated":[39],"efficient":[40],"by":[42,91],"hierarchal":[43,155],"approaches":[44,71],"consisting":[45],"of":[46,81],"path":[47,174],"planning":[48,101,124,175],"the":[50,58,62,66,74,82,104],"HL":[51,105,173],"representation":[52],"using":[54],"sub-goals":[55],"derived":[56],"from":[57],"plan":[59],"guide":[61],"RL":[63,156],"policy":[64,102,125],"source":[67],"task.":[68],"these":[70,89],"usually":[72],"neglect":[73],"complex":[75],"dynamics":[76,185],"sub-optimal":[78],"sub-goal-reaching":[79],"capabilities":[80,109],"robot":[83,108],"during":[84],"planning.":[85],"This":[86],"overcomes":[88],"limitations":[90],"proposing":[92],"novel":[94],"hierarchical":[95],"framework":[96],"that":[97],"utilizes":[98],"trainable":[100,172],"for":[103,178],"representation.":[106],"Thereby":[107],"environment":[111],"conditions":[112],"can":[113],"be":[114],"learned":[115,132],"utilizing":[116],"collected":[117],"rollout":[118],"data.":[119],"We":[120],"specifically":[121],"introduce":[122],"based":[126],"on":[127,151,157,169],"value":[128],"iteration":[129],"with":[130,153,171,182],"transition":[133],"model":[134],"(VI-RL).":[135],"In":[136],"simulated":[137],"VI-RL":[141],"results":[142],"consistent":[144],"strong":[145],"improvement":[146],"over":[147],"vanilla":[148,154],"RL,":[149],"par":[152,170],"single":[158],"layouts":[159],"but":[160],"more":[161],"broadly":[162],"applicable":[163],"multiple":[165],"layouts,":[166],"baselines":[176],"except":[177],"parking":[180],"difficult":[183],"non-holonomic":[184],"where":[186],"it":[187],"shows":[188],"marked":[189],"improvements.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}