{"id":"https://openalex.org/W4383108695","doi":"https://doi.org/10.1109/icra48891.2023.10160876","title":"Improving robot navigation in crowded environments using intrinsic rewards","display_name":"Improving robot navigation in crowded environments using intrinsic rewards","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108695","doi":"https://doi.org/10.1109/icra48891.2023.10160876"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160876","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":true,"oa_status":"green","oa_url":"https://zaguan.unizar.es/record/148224/files/texto_completo.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101541684","display_name":"Diego Mart\u00ednez","orcid":"https://orcid.org/0000-0002-2029-2851"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Diego Martinez-Baselga","raw_affiliation_strings":["Aragon Institute of Engineering Research (I3A), Universidad de Zaragoza,Robotics, Perception and Real Time Group,Zaragoza,Spain,50018"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aragon Institute of Engineering Research (I3A), Universidad de Zaragoza,Robotics, Perception and Real Time Group,Zaragoza,Spain,50018","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018256987","display_name":"Luis Riazuelo","orcid":"https://orcid.org/0000-0002-6722-5541"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luis Riazuelo","raw_affiliation_strings":["Aragon Institute of Engineering Research (I3A), Universidad de Zaragoza,Robotics, Perception and Real Time Group,Zaragoza,Spain,50018"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aragon Institute of Engineering Research (I3A), Universidad de Zaragoza,Robotics, Perception and Real Time Group,Zaragoza,Spain,50018","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110207791","display_name":"Luis Montano","orcid":null},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luis Montano","raw_affiliation_strings":["Aragon Institute of Engineering Research (I3A), Universidad de Zaragoza,Robotics, Perception and Real Time Group,Zaragoza,Spain,50018"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aragon Institute of Engineering Research (I3A), Universidad de Zaragoza,Robotics, Perception and Real Time Group,Zaragoza,Spain,50018","institution_ids":["https://openalex.org/I255234318"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I255234318"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9428","last_page":"9434"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9990000128746033,"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/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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":0.826887845993042},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7023925185203552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6906299591064453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5920358300209045},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5607877969741821},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.542743980884552},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.478930801153183},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.41887426376342773},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3848245441913605},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3345962464809418}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.826887845993042},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7023925185203552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6906299591064453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5920358300209045},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5607877969741821},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.542743980884552},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.478930801153183},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.41887426376342773},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3848245441913605},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3345962464809418},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"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":2,"locations":[{"id":"doi:10.1109/icra48891.2023.10160876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160876","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"},{"id":"pmh:oai:zaguan.unizar.es:148224","is_oa":true,"landing_page_url":"http://zaguan.unizar.es/record/148224","pdf_url":"https://zaguan.unizar.es/record/148224/files/texto_completo.pdf","source":{"id":"https://openalex.org/S4306401812","display_name":"Zaguan (University of Zaragoza Repository)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I255234318","host_organization_name":"Universidad de Zaragoza","host_organization_lineage":["https://openalex.org/I255234318"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:zaguan.unizar.es:148224","is_oa":true,"landing_page_url":"http://zaguan.unizar.es/record/148224","pdf_url":"https://zaguan.unizar.es/record/148224/files/texto_completo.pdf","source":{"id":"https://openalex.org/S4306401812","display_name":"Zaguan (University of Zaragoza Repository)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I255234318","host_organization_name":"Universidad de Zaragoza","host_organization_lineage":["https://openalex.org/I255234318"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4383108695.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W192919555","https://openalex.org/W1969483458","https://openalex.org/W1982809790","https://openalex.org/W1993411524","https://openalex.org/W2002440441","https://openalex.org/W2064675550","https://openalex.org/W2082585576","https://openalex.org/W2095705004","https://openalex.org/W2113256452","https://openalex.org/W2117211893","https://openalex.org/W2142943472","https://openalex.org/W2150468603","https://openalex.org/W2167052694","https://openalex.org/W2613088592","https://openalex.org/W2724169821","https://openalex.org/W2736601468","https://openalex.org/W2761873684","https://openalex.org/W2766836212","https://openalex.org/W2781726626","https://openalex.org/W2810439382","https://openalex.org/W2890001928","https://openalex.org/W2962954724","https://openalex.org/W2963523627","https://openalex.org/W2963809389","https://openalex.org/W2964043796","https://openalex.org/W2964067469","https://openalex.org/W2964319688","https://openalex.org/W2969277962","https://openalex.org/W2981759303","https://openalex.org/W3005857605","https://openalex.org/W3011877017","https://openalex.org/W3131623996","https://openalex.org/W3135883000","https://openalex.org/W3168856269","https://openalex.org/W3206270475","https://openalex.org/W3207293238","https://openalex.org/W4287867830","https://openalex.org/W4385245566","https://openalex.org/W6674330103","https://openalex.org/W6692846177","https://openalex.org/W6739901393","https://openalex.org/W6740092555","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6756303580","https://openalex.org/W6771807793","https://openalex.org/W6791110673"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2494202692"],"abstract_inverted_index":{"Autonomous":[0],"navigation":[1,206],"in":[2,20,67,70,204],"crowded":[3],"environments":[4],"is":[5],"an":[6],"open":[7],"problem":[8],"with":[9,90,97,161],"many":[10],"applications,":[11],"essential":[12],"for":[13,169],"the":[14,21,25,43,48,57,71,79,98,101,105,126,129,134,136,142,153,156,181,185,191,209],"coexistence":[15],"of":[16,24,56,128,132,155,180,187],"robots":[17],"and":[18,88,120,122,158,195,199],"humans":[19],"smart":[22],"cities":[23],"future.":[26],"In":[27,108],"recent":[28],"years,":[29],"deep":[30],"reinforcement":[31],"learning":[32,78],"approaches":[33],"have":[34],"proven":[35],"to":[36,53,86,116,144],"outperform":[37],"model-based":[38],"algorithms.":[39],"Nevertheless,":[40],"even":[41],"though":[42],"results":[44],"provided":[45],"are":[46,50,83,175],"promising,":[47],"works":[49],"not":[51,84],"able":[52,85],"take":[54],"advantage":[55],"capabilities":[58],"that":[59,74,165,184],"their":[60],"models":[61],"offer.":[62],"They":[63,82],"usually":[64],"get":[65,145],"trapped":[66],"local":[68],"optima":[69],"training":[72],"process,":[73],"prevent":[75],"them":[76],"from":[77],"optimal":[80],"policy.":[81],"visit":[87],"interact":[89],"every":[91],"possible":[92],"state":[93],"appropriately,":[94],"such":[95],"as":[96],"states":[99,130],"near":[100,104],"goal":[102],"or":[103],"dynamic":[106],"obstacles.":[107],"this":[109],"work,":[110],"we":[111],"propose":[112],"using":[113],"intrinsic":[114,188],"rewards":[115,189,198],"balance":[117],"between":[118],"exploration":[119,163],"exploitation":[121],"explore":[123],"depending":[124],"on":[125,133],"uncertainty":[127],"instead":[131],"time":[135],"agent":[137,143],"has":[138],"been":[139],"trained,":[140],"encouraging":[141],"more":[146],"curious":[147],"about":[148],"unknown":[149],"states.":[150],"We":[151],"explain":[152],"benefits":[154],"approach":[157],"compare":[159],"it":[160],"other":[162],"algorithms":[164,179],"may":[166],"be":[167],"used":[168],"crowd":[170],"navigation.":[171],"Many":[172],"simulation":[173],"experiments":[174],"performed":[176],"modifying":[177],"several":[178],"state-of-the-art,":[182],"showing":[183],"use":[186],"makes":[190],"robot":[192],"learn":[193],"faster":[194],"reach":[196],"higher":[197],"success":[200],"rates":[201],"(fewer":[202],"collisions)":[203],"shorter":[205],"times,":[207],"outperforming":[208],"state-of-the-art.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}