{"id":"https://openalex.org/W4416749788","doi":"https://doi.org/10.1109/iros60139.2025.11247153","title":"Disentangling Uncertainty for Safe Social Navigation using Deep Reinforcement Learning","display_name":"Disentangling Uncertainty for Safe Social Navigation using Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749788","doi":"https://doi.org/10.1109/iros60139.2025.11247153"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5056681387","display_name":"Daniel Fl\u00f6gel","orcid":"https://orcid.org/0009-0005-9899-0616"},"institutions":[{"id":"https://openalex.org/I143379178","display_name":"FZI Research Center for Information Technology","ror":"https://ror.org/04kdh6x72","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I143379178"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Daniel Fl\u00f6gel","raw_affiliation_strings":["FZI Research Center for Information Technology,Karlsruhe,Germany"],"affiliations":[{"raw_affiliation_string":"FZI Research Center for Information Technology,Karlsruhe,Germany","institution_ids":["https://openalex.org/I143379178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114387115","display_name":"Marcos G\u00f3mez Villafa\u00f1e","orcid":null},"institutions":[{"id":"https://openalex.org/I143379178","display_name":"FZI Research Center for Information Technology","ror":"https://ror.org/04kdh6x72","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I143379178"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marcos G\u00f3mez Villafa\u00f1e","raw_affiliation_strings":["FZI Research Center for Information Technology,Karlsruhe,Germany"],"affiliations":[{"raw_affiliation_string":"FZI Research Center for Information Technology,Karlsruhe,Germany","institution_ids":["https://openalex.org/I143379178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064819266","display_name":"Joshua Ransiek","orcid":null},"institutions":[{"id":"https://openalex.org/I143379178","display_name":"FZI Research Center for Information Technology","ror":"https://ror.org/04kdh6x72","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I143379178"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Joshua Ransiek","raw_affiliation_strings":["FZI Research Center for Information Technology,Karlsruhe,Germany"],"affiliations":[{"raw_affiliation_string":"FZI Research Center for Information Technology,Karlsruhe,Germany","institution_ids":["https://openalex.org/I143379178"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040502908","display_name":"S\u00f6ren Hohmann","orcid":"https://orcid.org/0000-0002-4170-1431"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"S\u00f6ren Hohmann","raw_affiliation_strings":["Institute of Control Systems at Karlsruhe Institute of Technology,Karlsruhe,Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Control Systems at Karlsruhe Institute of Technology,Karlsruhe,Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056681387"],"corresponding_institution_ids":["https://openalex.org/I143379178"],"apc_list":null,"apc_paid":null,"fwci":2.8331,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9317757,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"15014","last_page":"15021"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.30480000376701355,"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":0.30480000376701355,"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":0.22859999537467957,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.21649999916553497,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.682699978351593},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.6158000230789185},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5358999967575073},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4584999978542328},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.44920000433921814},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.42489999532699585},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.38190001249313354},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.3246000111103058},{"id":"https://openalex.org/keywords/social-robot","display_name":"Social robot","score":0.3089999854564667}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.682699978351593},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.6158000230789185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5809999704360962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.571399986743927},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5358999967575073},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4584999978542328},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4546000063419342},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.44920000433921814},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.42489999532699585},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.3246000111103058},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.3089999854564667},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3057999908924103},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C2779293179","wikidata":"https://www.wikidata.org/wiki/Q465266","display_name":"Social force model","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25699999928474426},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W192919555","https://openalex.org/W1992225177","https://openalex.org/W2236244207","https://openalex.org/W2734960757","https://openalex.org/W2949676527","https://openalex.org/W2951360122","https://openalex.org/W2963809389","https://openalex.org/W2964287316","https://openalex.org/W2968104655","https://openalex.org/W2981759303","https://openalex.org/W2998398431","https://openalex.org/W3091453879","https://openalex.org/W3131738409","https://openalex.org/W3134972302","https://openalex.org/W3142049818","https://openalex.org/W3152777725","https://openalex.org/W3154963698","https://openalex.org/W3158253560","https://openalex.org/W3196525377","https://openalex.org/W3206010851","https://openalex.org/W4236309383","https://openalex.org/W4285113711","https://openalex.org/W4306679387","https://openalex.org/W4310297558","https://openalex.org/W4315472129","https://openalex.org/W4362014203","https://openalex.org/W4383108497","https://openalex.org/W4383109557","https://openalex.org/W4384625456","https://openalex.org/W4387350805","https://openalex.org/W4388943201","https://openalex.org/W4398788580","https://openalex.org/W4399618549","https://openalex.org/W4401414359","https://openalex.org/W4403635664","https://openalex.org/W4405785175"],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"mobile":[1],"robots":[2],"are":[3,16],"increasingly":[4],"used":[5],"in":[6,30,46,157,197],"pedestrian-rich":[7],"environments":[8,199],"where":[9],"safe":[10,60,190],"navigation":[11,63,86],"and":[12,38,55,61,79,99,120,155,159,179],"appropriate":[13],"human":[14,53],"interaction":[15],"crucial.":[17],"While":[18],"Deep":[19],"Reinforcement":[20],"Learning":[21],"(DRL)":[22],"enables":[23],"socially":[24],"integrated":[25],"robot":[26,194],"behavior,":[27],"challenges":[28],"persist":[29],"novel":[31,73],"or":[32,52],"perturbed":[33,198],"scenarios":[34],"to":[35,50,124,137,143,177,184],"indicate":[36],"when":[37],"why":[39,59],"the":[40,102,115,126,129,139,162,169,181,185,189,193],"policy":[41,89],"is":[42,56,64,174],"uncertain.":[43],"Unknown":[44],"uncertainty":[45,81,91,182],"decision-making":[47,133],"can":[48,195],"lead":[49],"collisions":[51],"discomfort":[54],"one":[57],"reason":[58],"risk-aware":[62],"still":[65],"an":[66,166],"open":[67],"problem.":[68],"This":[69],"work":[70],"introduces":[71],"a":[72,84],"approach":[74],"that":[75,161],"integrates":[76],"aleatoric,":[77],"epistemic,":[78],"predictive":[80],"estimation":[82],"into":[83,101],"DRL":[85],"framework":[87],"for":[88],"distribution":[90],"estimates.":[92],"We,":[93],"therefore,":[94],"incorporate":[95],"Observation-Dependent":[96],"Variance":[97],"(ODV)":[98],"dropout":[100,122,156],"Proximal":[103],"Policy":[104],"Optimization":[105],"(PPO)":[106],"algorithm.":[107],"For":[108],"different":[109],"types":[110],"of":[111,117,128],"perturbations,":[112],"we":[113,135],"compare":[114],"ability":[116],"deep":[118],"ensembles":[119],"Monte-Carlo":[121],"(MC-dropout)":[123],"estimate":[125],"uncertainties":[127],"policy.":[130],"In":[131,171],"uncertain":[132],"situations,":[134],"propose":[136],"change":[138],"robot\u2019s":[140],"social":[141],"behavior":[142],"conservative":[144],"collision":[145],"avoidance.":[146],"The":[147],"results":[148],"show":[149],"improved":[150],"training":[151,163],"performance":[152],"with":[153,200],"ODV":[154],"PPO":[158],"reveal":[160],"scenario":[164],"has":[165],"impact":[167],"on":[168],"generalization.":[170],"addition,":[172],"MC-dropout":[173],"more":[175],"sensitive":[176],"perturbations":[178],"correlates":[180],"type":[183],"perturbation":[186],"better.":[187],"With":[188],"action":[191],"selection,":[192],"navigate":[196],"fewer":[201],"collisions.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}