{"id":"https://openalex.org/W4416749616","doi":"https://doi.org/10.1109/iros60139.2025.11246010","title":"Modeling Deception in Multi-Robot Target-Attacker-Defender Game via Deep Reinforcement Learning","display_name":"Modeling Deception in Multi-Robot Target-Attacker-Defender Game via Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749616","doi":"https://doi.org/10.1109/iros60139.2025.11246010"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246010","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/A5088439780","display_name":"Fandi Gou","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fandi Gou","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Automation and Intelligent Sensing,Shanghai,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Automation and Intelligent Sensing,Shanghai,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069998161","display_name":"Chenyu Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyu Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Automation and Intelligent Sensing,Shanghai,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Automation and Intelligent Sensing,Shanghai,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065262820","display_name":"Haikuo Du","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haikuo Du","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Automation and Intelligent Sensing,Shanghai,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Automation and Intelligent Sensing,Shanghai,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012941986","display_name":"Yunze Cai","orcid":"https://orcid.org/0000-0002-1783-2984"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunze Cai","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Automation and Intelligent Sensing,Shanghai,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Automation and Intelligent Sensing,Shanghai,200240","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42430308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"813","last_page":"819"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.42260000109672546,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.42260000109672546,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0982000008225441,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0617000013589859,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/deception","display_name":"Deception","score":0.934499979019165},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6696000099182129},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.49239999055862427},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4846999943256378},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3926999866962433},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.3398999869823456}],"concepts":[{"id":"https://openalex.org/C2779267917","wikidata":"https://www.wikidata.org/wiki/Q170028","display_name":"Deception","level":2,"score":0.934499979019165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.683899998664856},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6696000099182129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5575000047683716},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3418999910354614},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2743000090122223}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246010","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/F4320322857","display_name":"Aeronautical Science Foundation of China","ror":"https://ror.org/02wq41p38"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1972770177","https://openalex.org/W2030140501","https://openalex.org/W2051537666","https://openalex.org/W2525818861","https://openalex.org/W2783963839","https://openalex.org/W2800797998","https://openalex.org/W2885195348","https://openalex.org/W2911234349","https://openalex.org/W2963978778","https://openalex.org/W3017102765","https://openalex.org/W3112673853","https://openalex.org/W3112680002","https://openalex.org/W3118247724","https://openalex.org/W3128168044","https://openalex.org/W3185539947","https://openalex.org/W3197787153","https://openalex.org/W3210221681","https://openalex.org/W4295768108","https://openalex.org/W4387745899","https://openalex.org/W4389989752","https://openalex.org/W4390587522","https://openalex.org/W4400957290"],"related_works":[],"abstract_inverted_index":{"Deception":[0],"is":[1],"a":[2,21,41,65,136],"crucial":[3],"strategy":[4],"in":[5,11,20,142,148],"adversarial":[6],"scenarios,":[7],"yet":[8],"its":[9],"application":[10],"multi-agent":[12,47,143,150],"confrontations":[13],"remains":[14],"understudied.":[15],"This":[16,133],"paper":[17],"investigates":[18],"deception":[19,37,99,141],"multi-robot":[22],"Target-Attacker-Defender":[23],"(MR-TAD)":[24],"game,":[25],"where":[26],"Attackers":[27],"aim":[28],"to":[29,82,115],"capture":[30],"Targets":[31],"while":[32],"evading":[33],"Defenders.":[34],"To":[35],"model":[36],"effectively,":[38],"we":[39,63],"propose":[40],"hierarchical":[42],"decision-making":[43],"framework":[44,138],"that":[45,97],"integrates":[46],"reinforcement":[48],"learning":[49],"(MARL)":[50],"for":[51,58,139],"high-level":[52],"deceptive":[53,87],"strategies":[54],"and":[55,78],"optimal":[56],"control":[57],"low-level":[59],"motion":[60],"control.":[61],"Furthermore,":[62],"introduce":[64],"novel":[66],"composite":[67],"deception-oriented":[68],"reward":[69],"function,":[70],"which":[71],"combines":[72],"hitting":[73],"rewards,":[74,77],"belief":[75],"switch":[76],"position":[79],"advantage":[80],"rewards":[81],"facilitate":[83],"the":[84,102,127,130],"training":[85],"of":[86,94,105,111,129],"behaviors.":[88],"Simulation":[89],"results":[90],"across":[91],"varying":[92],"numbers":[93],"robots":[95,124],"demonstrate":[96],"incorporating":[98],"significantly":[100],"increases":[101],"success":[103],"rate":[104],"Attackers,":[106],"with":[107,121,145],"an":[108],"average":[109],"improvement":[110],"over":[112],"70%":[113],"compared":[114],"non-deceptive":[116],"strategies.":[117],"Additionally,":[118],"real-world":[119],"experiments":[120],"omnidirectional":[122],"mobile":[123],"further":[125],"confirm":[126],"effectiveness":[128],"proposed":[131],"method.":[132],"study":[134],"establishes":[135],"generalizable":[137],"modeling":[140],"systems,":[144],"potential":[146],"applications":[147],"various":[149],"scenarios.":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}