{"id":"https://openalex.org/W7130568340","doi":"https://doi.org/10.48550/arxiv.2602.16353","title":"Dual-Quadruped Collaborative Transportation in Narrow Environments via Safe Reinforcement Learning","display_name":"Dual-Quadruped Collaborative Transportation in Narrow Environments via Safe Reinforcement Learning","alternate_titles":[],"publication_year":2026,"publication_date":"2026-02-18","ids":{"openalex":"https://openalex.org/W7130568340","doi":"https://doi.org/10.48550/arxiv.2602.16353"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.16353","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.16353","pdf_url":"https://arxiv.org/pdf/2602.16353","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"parent_works":[],"lineage":["https://openalex.org/W7130568340"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.16353","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115863089","display_name":"Zhezhi Lei","orcid":"https://orcid.org/0009-0001-3907-7641","observed_orcids":["https://orcid.org/0009-0001-3907-7641"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Zhezhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038926322","display_name":"Zhihai Bi","orcid":"https://orcid.org/0009-0001-0831-216X","observed_orcids":["https://orcid.org/0009-0001-0831-216X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bi, Zhihai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126388627","display_name":"Wenxin Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053340150","display_name":"Jun Ma","orcid":"https://orcid.org/0000-0002-9405-8232","observed_orcids":["https://orcid.org/0000-0002-9405-8232"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9789999723434448,"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":0.9789999723434448,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.011099999770522118,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.004399999976158142,"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/collaborative-transportation","display_name":"collaborative transportation","score":0.9279999732971191},{"id":"https://openalex.org/keywords/safe-reinforcement-learning","display_name":"safe reinforcement learning","score":0.9190000295639038},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"collision avoidance","score":0.7680000066757202},{"id":"https://openalex.org/keywords/task-allocation","display_name":"task allocation","score":0.7419999837875366},{"id":"https://openalex.org/keywords/narrow-environments","display_name":"narrow environments","score":0.8690000176429749},{"id":"https://openalex.org/keywords/multi-robot-collaboration","display_name":"multi-robot collaboration","score":0.781000018119812}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7842000126838684},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7178999781608582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6887999773025513},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.5831999778747559},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5699999928474426},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4884999990463257},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.420199990272522},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C138020889","wikidata":"https://www.wikidata.org/wiki/Q2349659","display_name":"Collaborative learning","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C2780595565","wikidata":"https://www.wikidata.org/wiki/Q5145833","display_name":"Collaborative engineering","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3176000118255615},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.30489999055862427},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.2847999930381775},{"id":"https://openalex.org/C539828613","wikidata":"https://www.wikidata.org/wiki/Q178512","display_name":"Public transport","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C554579003","wikidata":"https://www.wikidata.org/wiki/Q474157","display_name":"Collaborative software","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2540999948978424},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.16353","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.16353","pdf_url":"https://arxiv.org/pdf/2602.16353","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2602.16353","doi":"https://doi.org/10.48550/arxiv.2602.16353","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.16353","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.16353","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.16353","pdf_url":"https://arxiv.org/pdf/2602.16353","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7130568340.pdf","grobid_xml":"https://content.openalex.org/works/W7130568340.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2999446437","https://openalex.org/W3043763914","https://openalex.org/W3045059767","https://openalex.org/W3204798791","https://openalex.org/W3205685096","https://openalex.org/W4285102391","https://openalex.org/W4310886200","https://openalex.org/W4327571609","https://openalex.org/W4366310810","https://openalex.org/W4386501335","https://openalex.org/W4387546354","https://openalex.org/W4396542390","https://openalex.org/W4401325761","https://openalex.org/W4401358290","https://openalex.org/W4401415617","https://openalex.org/W4405313645","https://openalex.org/W4406322086","https://openalex.org/W4412605577","https://openalex.org/W4413104935","https://openalex.org/W4413917684","https://openalex.org/W7133226216"],"related_works":["https://openalex.org/W4405313645","https://openalex.org/W7140308612","https://openalex.org/W7220947390","https://openalex.org/W3204798791","https://openalex.org/W7161718435","https://openalex.org/W7116878463","https://openalex.org/W4414432859","https://openalex.org/W6967115787","https://openalex.org/W7169845158","https://openalex.org/W4409426579"],"abstract_inverted_index":{"Collaborative":[0],"transportation,":[1],"where":[2,37,74],"multiple":[3],"robots":[4,121],"collaboratively":[5],"transport":[6],"a":[7,50,68,83,111,152],"payload,":[8],"has":[9],"garnered":[10],"significant":[11],"attention":[12],"in":[13,34,156],"recent":[14],"years.":[15],"While":[16],"ensuring":[17],"safe":[18,58],"and":[19,139,151],"high-performance":[20],"inter-robot":[21],"collaboration":[22],"is":[23,30,41,77],"critical":[24],"for":[25,53],"effective":[26],"task":[27,66,102,126,136],"execution,":[28],"it":[29],"difficult":[31],"to":[32,94,119,122,161],"pursue":[33],"narrow":[35],"environments":[36],"the":[38,65,89,124,145],"feasible":[39],"region":[40],"extremely":[42],"limited.":[43],"To":[44],"address":[45],"this":[46],"challenge,":[47],"we":[48,63,109],"propose":[49,110],"novel":[51],"approach":[52,147],"dual-quadruped":[54,157],"collaborative":[55,135,158],"transportation":[56,159],"via":[57],"reinforcement":[59],"learning":[60],"(RL).":[61],"Specifically,":[62],"model":[64],"as":[67,79],"fully":[69],"cooperative":[70],"constrained":[71],"Markov":[72],"game,":[73],"collision":[75],"avoidance":[76],"formulated":[78],"constraints.":[80],"We":[81],"introduce":[82],"cost-advantage":[84],"decomposition":[85],"method":[86,114],"that":[87,115,144],"enforces":[88],"sum":[90],"of":[91],"team":[92],"constraints":[93,118],"remain":[95],"below":[96],"an":[97,105],"upper":[98],"bound,":[99],"thereby":[100,133],"guaranteeing":[101],"safety":[103],"within":[104],"RL":[106],"framework.":[107],"Furthermore,":[108],"constraint":[112],"allocation":[113],"assigns":[116],"shared":[117],"individual":[120],"maximize":[123],"overall":[125],"reward,":[127],"encouraging":[128],"autonomous":[129],"task-assignment":[130],"among":[131],"robots,":[132],"improving":[134],"performance.":[137],"Simulation":[138],"real-time":[140],"experimental":[141],"results":[142],"demonstrate":[143],"proposed":[146],"achieves":[148],"superior":[149],"performance":[150],"higher":[153],"success":[154],"rate":[155],"compared":[160],"existing":[162],"methods.":[163]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7130568340","counts_by_year":[],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2026-02-20T00:00:00"}
