{"id":"https://openalex.org/W4320027761","doi":"https://doi.org/10.1109/robio55434.2022.10011912","title":"Multiple Subgoals-guided Hierarchical Learning in Robot Navigation","display_name":"Multiple Subgoals-guided Hierarchical Learning in Robot Navigation","publication_year":2022,"publication_date":"2022-12-05","ids":{"openalex":"https://openalex.org/W4320027761","doi":"https://doi.org/10.1109/robio55434.2022.10011912"},"language":"en","primary_location":{"id":"doi:10.1109/robio55434.2022.10011912","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio55434.2022.10011912","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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 International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.rug.nl/en/publications/0c66f55f-da29-4493-80c8-b5b3f5d5d7c6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014099627","display_name":"Sha Luo","orcid":"https://orcid.org/0000-0001-8942-8350"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Sha Luo","raw_affiliation_strings":["University of Groningen,Department of Artificial Intelligence,Groningen,The Netherlands,9712 CP"],"affiliations":[{"raw_affiliation_string":"University of Groningen,Department of Artificial Intelligence,Groningen,The Netherlands,9712 CP","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028858025","display_name":"Lambert Schomaker","orcid":"https://orcid.org/0000-0003-2351-930X"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lambert Schomaker","raw_affiliation_strings":["University of Groningen,Department of Artificial Intelligence,Groningen,The Netherlands,9712 CP"],"affiliations":[{"raw_affiliation_string":"University of Groningen,Department of Artificial Intelligence,Groningen,The Netherlands,9712 CP","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014099627"],"corresponding_institution_ids":["https://openalex.org/I169381384"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21486508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"9","last_page":"14"},"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":0.9997000098228455,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9969000220298767,"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":0.803974449634552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7422947883605957},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.6085041165351868},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5647668838500977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.54826819896698},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5430000424385071},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4206928014755249},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.41885846853256226},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.412354052066803},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38333579897880554},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3648180067539215},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13241273164749146}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.803974449634552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422947883605957},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.6085041165351868},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5647668838500977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.54826819896698},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5430000424385071},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4206928014755249},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.41885846853256226},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.412354052066803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38333579897880554},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3648180067539215},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13241273164749146},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/robio55434.2022.10011912","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio55434.2022.10011912","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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 International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:publications/0c66f55f-da29-4493-80c8-b5b3f5d5d7c6","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/0c66f55f-da29-4493-80c8-b5b3f5d5d7c6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Luo, S & Schomaker, L 2023, Multiple Subgoals-guided Hierarchical Learning in Robot Navigation. in 2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022. 2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022, Institute of Electrical and Electronics Engineers Inc., pp. 9-14, 2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022, Jinghong, China, 05/12/2022. https://doi.org/10.1109/ROBIO55434.2022.10011912","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/0c66f55f-da29-4493-80c8-b5b3f5d5d7c6","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/0c66f55f-da29-4493-80c8-b5b3f5d5d7c6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"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":"Luo, S & Schomaker, L 2023, Multiple Subgoals-guided Hierarchical Learning in Robot Navigation. in 2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022. 2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022, Institute of Electrical and Electronics Engineers Inc., pp. 9-14, 2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022, Jinghong, China, 05/12/2022. https://doi.org/10.1109/ROBIO55434.2022.10011912","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.rug.nl:publications/0c66f55f-da29-4493-80c8-b5b3f5d5d7c6","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/0c66f55f-da29-4493-80c8-b5b3f5d5d7c6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Luo, S & Schomaker, L 2023, Multiple Subgoals-guided Hierarchical Learning in Robot Navigation. in 2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022. 2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022, Institute of Electrical and Electronics Engineers Inc., pp. 9-14, 2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022, Jinghong, China, 05/12/2022. https://doi.org/10.1109/ROBIO55434.2022.10011912","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W571818863","https://openalex.org/W1592847719","https://openalex.org/W2145339207","https://openalex.org/W2736601468","https://openalex.org/W2739330054","https://openalex.org/W2766447205","https://openalex.org/W2775496939","https://openalex.org/W2781726626","https://openalex.org/W2886380293","https://openalex.org/W2902907165","https://openalex.org/W2904246096","https://openalex.org/W2945263287","https://openalex.org/W2948479456","https://openalex.org/W2949604932","https://openalex.org/W2950614095","https://openalex.org/W2953511201","https://openalex.org/W2963262099","https://openalex.org/W2963842088","https://openalex.org/W3034563340","https://openalex.org/W3103833006","https://openalex.org/W3132442447","https://openalex.org/W4288021424","https://openalex.org/W4294578467","https://openalex.org/W6703271639","https://openalex.org/W6729130418","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6752089545","https://openalex.org/W6753938571","https://openalex.org/W6759871227","https://openalex.org/W6762388393","https://openalex.org/W6767649332"],"related_works":["https://openalex.org/W1568779110","https://openalex.org/W804484174","https://openalex.org/W4231704780","https://openalex.org/W4244698559","https://openalex.org/W4246538999","https://openalex.org/W2083794993","https://openalex.org/W56933075","https://openalex.org/W4399598005","https://openalex.org/W2002361198","https://openalex.org/W352609212"],"abstract_inverted_index":{"Solving":[0],"obstacle-clustered":[1],"robotic":[2],"navigation":[3,64],"tasks":[4],"via":[5],"model-free":[6],"reinforcement":[7],"learning":[8,26],"(RL)":[9],"is":[10,34,57],"challenging":[11],"due":[12],"to":[13,84,101,150],"the":[14,35,38,45,54,85,91,97,102,106,113,121,130],"extended":[15],"decision":[16],"horizon":[17],"and":[18,41,74,119,123,145],"sparse":[19],"rewards.":[20],"Previous":[21],"work":[22,60],"has":[23],"demonstrated":[24],"efficient":[25],"with":[27],"single":[28],"subgoal-conditioned":[29],"hierarchical":[30],"approaches.":[31],"The":[32,134],"subgoal":[33,56,93,98],"action":[36],"from":[37],"high-level":[39,70],"policy":[40,52],"it":[42],"operates":[43],"on":[44,129],"low-level":[46,76,86],"module,":[47],"which":[48,66],"could":[49,89,111,139],"invoke":[50],"sub-optimal":[51],"when":[53],"selected":[55],"suboptimal.":[58],"This":[59],"introduces":[61],"multiple":[62,71,82,109],"subgoals-guided":[63],"(MSGN)":[65],"consists":[67],"of":[68],"a":[69,75,141],"subgoals":[72,83,110],"Planner":[73],"goal-conditioned":[77,114],"RL":[78,103,115],"Controller.":[79],"By":[80],"passing":[81],"agent,":[87],"MSGN":[88,138],"alleviate":[90],"suboptimal":[92],"problem":[94],"by":[95],"transferring":[96],"selection":[99],"process":[100],"agent.":[104],"At":[105],"same":[107],"time,":[108],"help":[112],"agent":[116],"better":[117],"explore":[118],"understand":[120],"environment":[122],"task.":[124],"We":[125],"tested":[126],"our":[127],"method":[128],"Safety":[131],"Gym":[132],"suite.":[133],"results":[135],"verified":[136],"that":[137],"achieve":[140],"higher":[142],"success":[143],"rate":[144],"lower":[146],"collision":[147],"cost":[148],"compared":[149],"baselines.":[151]},"counts_by_year":[],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}