{"id":"https://openalex.org/W4416750386","doi":"https://doi.org/10.1109/iros60139.2025.11247307","title":"Enhancing Deep Reinforcement Learning-based Robot Navigation Generalization through Scenario Augmentation","display_name":"Enhancing Deep Reinforcement Learning-based Robot Navigation Generalization through Scenario Augmentation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750386","doi":"https://doi.org/10.1109/iros60139.2025.11247307"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247307","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/A5113127926","display_name":"Shanze Wang","orcid":"https://orcid.org/0009-0001-4004-1056"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Shanze Wang","raw_affiliation_strings":["Hong Kong Polytechnic University,Department of Aeronautical & Aviation Engineering (AAE) and the Research Centre for Unmanned Autonomous Systems (RCUAS),Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University,Department of Aeronautical & Aviation Engineering (AAE) and the Research Centre for Unmanned Autonomous Systems (RCUAS),Hong Kong,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108821387","display_name":"Mingao Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingao Tan","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Institute of Digital Twin,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Institute of Digital Twin,Ningbo,China","institution_ids":["https://openalex.org/I4210165339"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003027050","display_name":"Zhibo Yang","orcid":"https://orcid.org/0000-0001-9454-4532"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhibo Yang","raw_affiliation_strings":["National University of Singapore,Department of Mechanical Engineering"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Mechanical Engineering","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101678731","display_name":"Xianghui Wang","orcid":"https://orcid.org/0000-0003-1066-8787"},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianghui Wang","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Institute of Digital Twin,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Institute of Digital Twin,Ningbo,China","institution_ids":["https://openalex.org/I4210165339"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102500550","display_name":"Xiaoyu Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Shen","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Institute of Digital Twin,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Institute of Digital Twin,Ningbo,China","institution_ids":["https://openalex.org/I4210165339"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037131765","display_name":"Hailong Huang","orcid":"https://orcid.org/0000-0003-2667-6423"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hailong Huang","raw_affiliation_strings":["Hong Kong Polytechnic University,Department of Aeronautical & Aviation Engineering (AAE) and the Research Centre for Unmanned Autonomous Systems (RCUAS),Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University,Department of Aeronautical & Aviation Engineering (AAE) and the Research Centre for Unmanned Autonomous Systems (RCUAS),Hong Kong,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057842914","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-8415-1062"},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Institute of Digital Twin,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Institute of Digital Twin,Ningbo,China","institution_ids":["https://openalex.org/I4210165339"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5113127926"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":2.3568,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91963006,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"935","last_page":"942"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7687000036239624,"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":0.7687000036239624,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.059300001710653305,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.0430000014603138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.8136000037193298},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6969000101089478},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6635000109672546},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5809000134468079},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.391400009393692},{"id":"https://openalex.org/keywords/navigation-system","display_name":"Navigation system","score":0.35899999737739563},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3578999936580658}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8136000037193298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7361000180244446},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6969000101089478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.678600013256073},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6635000109672546},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5809000134468079},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38510000705718994},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3626999855041504},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3578999936580658},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.32580000162124634},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31360000371932983},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.2669999897480011},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.2506999969482422},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247307","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":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2082511574","https://openalex.org/W2117211893","https://openalex.org/W2143864104","https://openalex.org/W2145339207","https://openalex.org/W2795561664","https://openalex.org/W2919115771","https://openalex.org/W2951360122","https://openalex.org/W2960705509","https://openalex.org/W2962887844","https://openalex.org/W2963129648","https://openalex.org/W2963428623","https://openalex.org/W2969277962","https://openalex.org/W3012783233","https://openalex.org/W3031798691","https://openalex.org/W3094551248","https://openalex.org/W3193320876","https://openalex.org/W3196603038","https://openalex.org/W3204518412","https://openalex.org/W4315487473","https://openalex.org/W4362014203","https://openalex.org/W4362580653","https://openalex.org/W4383066576","https://openalex.org/W4386051596","https://openalex.org/W4386634158","https://openalex.org/W4387350805","https://openalex.org/W4399562809","https://openalex.org/W4403209986","https://openalex.org/W4403982072"],"related_works":[],"abstract_inverted_index":{"This":[0],"work":[1],"focuses":[2],"on":[3,58],"enhancing":[4],"the":[5,38,46,69,85,103,118],"generalization":[6,119],"performance":[7,133],"of":[8,88,121],"deep":[9,122],"reinforcement":[10,123],"learning-based":[11,124],"robot":[12],"navigation":[13,90,125,129,141],"in":[14,73,92,143],"unseen":[15,93],"environments.":[16,94],"We":[17],"present":[18],"a":[19],"novel":[20],"data":[21],"augmentation":[22,115],"approach":[23],"called":[24],"scenario":[25,76,114],"augmentation,":[26,77],"which":[27],"enables":[28],"robots":[29],"to":[30,68,83],"navigate":[31],"effectively":[32],"across":[33],"diverse":[34],"settings":[35],"without":[36],"altering":[37],"training":[39,100],"scenario.":[40],"The":[41,127],"method":[42],"operates":[43],"by":[44,134],"mapping":[45],"robot\u2019s":[47],"observation":[48],"into":[49],"an":[50,54],"imagined":[51,55],"space,":[52],"generating":[53],"action":[56,66,71],"based":[57],"this":[59,65],"transformed":[60],"observation,":[61],"and":[62],"then":[63],"remapping":[64],"back":[67],"real":[70],"executed":[72],"simulation.":[74],"Through":[75],"we":[78],"conduct":[79],"extensive":[80],"comparative":[81],"experiments":[82],"investigate":[84],"underlying":[86],"causes":[87],"suboptimal":[89],"behaviors":[91],"Our":[95],"analysis":[96],"indicates":[97],"that":[98,113],"limited":[99],"scenarios":[101],"represent":[102],"primary":[104],"factor":[105],"behind":[106],"these":[107],"undesired":[108],"behaviors.":[109],"Experimental":[110],"results":[111],"confirm":[112],"substantially":[116],"enhances":[117],"capabilities":[120],"systems.":[126],"improved":[128],"framework":[130],"demonstrates":[131],"exceptional":[132],"producing":[135],"near-optimal":[136],"trajectories":[137],"with":[138],"significantly":[139],"reduced":[140],"time":[142],"real-world":[144],"applications.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}