{"id":"https://openalex.org/W4414032867","doi":"https://doi.org/10.1109/rcar65431.2025.11139421","title":"Multi-robot Collision Avoidance in Non-communication Deep-Sea Environments via Reinforcement Learning","display_name":"Multi-robot Collision Avoidance in Non-communication Deep-Sea Environments via Reinforcement Learning","publication_year":2025,"publication_date":"2025-06-01","ids":{"openalex":"https://openalex.org/W4414032867","doi":"https://doi.org/10.1109/rcar65431.2025.11139421"},"language":"en","primary_location":{"id":"doi:10.1109/rcar65431.2025.11139421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar65431.2025.11139421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Real-time Computing and Robotics (RCAR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5067819355","display_name":"Daoheng Li","orcid":"https://orcid.org/0009-0009-5754-8556"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daoheng Li","raw_affiliation_strings":["Tsinghua University,Department of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050646031","display_name":"Qingqi Zhang","orcid":"https://orcid.org/0009-0006-8043-2007"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingqi Zhang","raw_affiliation_strings":["Tsinghua University,Department of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101689420","display_name":"Yue Ma","orcid":"https://orcid.org/0000-0002-9581-6189"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Ma","raw_affiliation_strings":["Tsinghua University,Department of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069546592","display_name":"Shu Miao","orcid":"https://orcid.org/0000-0002-0286-2507"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu Miao","raw_affiliation_strings":["Tsinghua University,Department of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107954261","display_name":"Xiang Li","orcid":"https://orcid.org/0009-0006-5751-7600"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Tsinghua University,Department of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068624597","display_name":"Shiji Song","orcid":"https://orcid.org/0000-0001-7361-9283"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiji Song","raw_affiliation_strings":["Tsinghua University,Department of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1259","last_page":"1264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9842000007629395,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9842000007629395,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.9758999943733215,"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"}},{"id":"https://openalex.org/T10917","display_name":"Smart Grid Security and Resilience","score":0.9731000065803528,"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/collision-avoidance","display_name":"Collision avoidance","score":0.8579970598220825},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7980850338935852},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.658507764339447},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6405495405197144},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.579088032245636},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4319073259830475},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42934876680374146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42491716146469116},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.13952207565307617}],"concepts":[{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.8579970598220825},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7980850338935852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.658507764339447},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6405495405197144},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.579088032245636},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4319073259830475},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42934876680374146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42491716146469116},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.13952207565307617}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rcar65431.2025.11139421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar65431.2025.11139421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Real-time Computing and Robotics (RCAR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W178419168","https://openalex.org/W192919555","https://openalex.org/W1969142081","https://openalex.org/W2071005201","https://openalex.org/W2227909145","https://openalex.org/W2800330536","https://openalex.org/W2913190903","https://openalex.org/W2963821308","https://openalex.org/W2981759303","https://openalex.org/W3040817486","https://openalex.org/W3100789280","https://openalex.org/W3131290367","https://openalex.org/W3173185086","https://openalex.org/W4220817121","https://openalex.org/W4251549492","https://openalex.org/W4312419387","https://openalex.org/W4382202869","https://openalex.org/W4382202901","https://openalex.org/W4401417008"],"related_works":["https://openalex.org/W4317634134","https://openalex.org/W2981729160","https://openalex.org/W4310743282","https://openalex.org/W1819938260","https://openalex.org/W2340892746","https://openalex.org/W3163022373","https://openalex.org/W2742483371","https://openalex.org/W3005999311","https://openalex.org/W2122871747","https://openalex.org/W3114279067"],"abstract_inverted_index":{"Ensuring":[0],"effective":[1],"multi-robot":[2,56],"collision":[3],"avoidance":[4],"in":[5,125],"deep-sea":[6],"environments":[7,82],"presents":[8],"unique":[9],"challenges":[10],"due":[11],"to":[12,31,70,78,80,100],"the":[13,19],"absence":[14],"of":[15,21,37,73],"direct":[16],"communication":[17,84],"and":[18,34,95,122],"intermittency":[20],"positional":[22],"updates.":[23,108],"Existing":[24],"methods":[25],"struggle":[26],"with":[27,105],"outdated":[28],"information,":[29,75],"leading":[30],"suboptimal":[32],"decision-making":[33],"increased":[35],"risk":[36],"collisions.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"address":[43],"these":[44],"issues":[45],"by":[46],"introducing":[47],"a":[48,64],"multi-agent":[49],"reinforcement":[50],"learning":[51],"(MARL)-based":[52],"framework":[53],"tailored":[54],"for":[55],"navigation":[57],"under":[58],"intermittent":[59],"observations.":[60],"Our":[61],"approach":[62,113],"incorporates":[63],"recurrent":[65],"neural":[66],"network":[67],"(RNN)-based":[68],"module":[69],"take":[71],"advantage":[72],"historical":[74],"enabling":[76],"agents":[77],"adapt":[79],"dynamic":[81],"despite":[83],"constraints.":[85],"By":[86],"leveraging":[87],"MARL,":[88],"our":[89,112],"method":[90],"effectively":[91],"balances":[92],"safety,":[93],"efficiency,":[94],"path":[96],"optimality,":[97],"allowing":[98],"robots":[99],"make":[101],"informed":[102],"decisions":[103],"even":[104],"limited":[106],"sensing":[107],"Simulations":[109],"demonstrate":[110],"that":[111],"significantly":[114],"outperforms":[115],"existing":[116],"baselines,":[117],"achieving":[118],"higher":[119],"success":[120],"rates":[121],"improved":[123],"adaptability":[124],"high-density,":[126],"long-interval":[127],"scenarios.":[128]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}