{"id":"https://openalex.org/W7164845372","doi":"https://doi.org/10.1109/tase.2026.3703136","title":"KinematicRL: A Sim-to-Real Reinforcement Learning Framework for Social Navigation With Kinodynamic Feasibility","display_name":"KinematicRL: A Sim-to-Real Reinforcement Learning Framework for Social Navigation With Kinodynamic Feasibility","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7164845372","doi":"https://doi.org/10.1109/tase.2026.3703136"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2026.3703136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3703136","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-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/A5057628847","display_name":"Zhiming Xu","orcid":"https://orcid.org/0000-0002-3306-8023"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiming Xu","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-3382-8474","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046308214","display_name":"Haodong Yang","orcid":"https://orcid.org/0009-0007-9104-9430"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haodong Yang","raw_affiliation_strings":["Department of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-9104-9430","affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037285766","display_name":"Chengju Liu","orcid":"https://orcid.org/0000-0001-7543-0855"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengju Liu","raw_affiliation_strings":["Department of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7543-0855","affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073789459","display_name":"Qijun Chen","orcid":"https://orcid.org/0000-0001-5644-1188"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qijun Chen","raw_affiliation_strings":["Department of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5644-1188","affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011215159","display_name":"Chenpeng Yao","orcid":"https://orcid.org/0000-0002-6804-3539"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenpeng Yao","raw_affiliation_strings":["Department of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6804-3539","affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79281992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"11824","last_page":"11839"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.2583000063896179,"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"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.2583000063896179,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2434999942779541,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.22499999403953552,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.5321000218391418},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3490000069141388},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.3310000002384186},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.32269999384880066},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3077000081539154},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.2879999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6136999726295471},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5321000218391418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.51910001039505},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3490000069141388},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.3310000002384186},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3303999900817871},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3273000121116638},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.27320000529289246},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2026.3703136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3703136","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7403551936149597}],"awards":[{"id":"https://openalex.org/G1767306556","display_name":null,"funder_award_id":"62403358","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G500374774","display_name":null,"funder_award_id":"62333017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5736016220","display_name":null,"funder_award_id":"62233013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(DRL)":[3],"has":[4],"shown":[5],"promise":[6],"for":[7,49,179],"social":[8,180],"navigation,":[9],"yet":[10],"its":[11],"real-world":[12,50,200],"deployment":[13],"remains":[14],"hindered":[15],"by":[16,94],"a":[17,35,95,107,121,216],"persistent":[18],"sim-to-real":[19],"gap":[20],"arising":[21],"from":[22],"simplified":[23],"first-order":[24],"dynamics":[25],"and":[26,61,141,150,169,190],"context-specific":[27],"human":[28,123],"state":[29],"estimation":[30],"pipelines.":[31],"This":[32],"work":[33],"presents":[34],"unified":[36],"framework":[37],"that":[38,56,102],"addresses":[39],"these":[40],"limitations":[41],"to":[42,87,112,137,166,192],"produce":[43],"dynamically":[44],"feasible":[45],"navigation":[46],"policies":[47],"suitable":[48],"deployment.":[51],"First,":[52],"theoretical":[53],"analysis":[54],"reveals":[55],"tracking":[57,124,209],"error":[58],"between":[59],"simulated":[60],"actual":[62],"robot":[63,220],"position":[64],"decays":[65],"exponentially":[66],"with":[67,206,221],"increased":[68],"control":[69,76,84],"order,":[70],"motivating":[71],"the":[72,104,114,207],"use":[73],"of":[74,118,147,195],"higher-order":[75],"inputs":[77],"as":[78],"DRL":[79],"action":[80],"space.":[81],"A":[82],"second-order":[83],"formulation":[85],"tailored":[86],"differential":[88,218],"drive":[89,219],"robots":[90],"is":[91,130],"developed,":[92],"complemented":[93],"stochastic":[96],"iterative":[97],"Linear":[98],"Quadratic":[99],"Regulator":[100],"(iLQR)":[101],"pretrains":[103],"policy":[105],"via":[106],"divergence":[108],"minimization":[109],"objective.":[110],"Second,":[111],"avoid":[113],"added":[115],"system":[116],"complexity":[117],"camera-LiDAR":[119],"fusion,":[120],"cluster-based":[122],"pipeline":[125],"using":[126],"only":[127],"2D":[128],"LiDAR":[129],"introduced.":[131],"Human":[132],"detections":[133],"are":[134],"associated":[135],"according":[136],"both":[138,177],"spatial":[139],"proximity":[140],"velocity":[142,153],"similarity,":[143],"enabling":[144],"reliable":[145],"differentiation":[146],"nearby":[148],"pedestrians":[149],"yielding":[151],"stable":[152],"estimates":[154],"through":[155],"temporal":[156],"aggregation.":[157],"Third,":[158],"we":[159],"introduce":[160],"an":[161],"unbiased":[162],"residual":[163],"gating":[164],"block":[165],"balance":[167],"reaction-":[168],"memory-based":[170],"behaviors":[171],"while":[172],"handling":[173],"time-varying":[174],"crowd":[175],"sizes,":[176],"critical":[178],"navigation.":[181],"The":[182],"resulting":[183],"policy,":[184],"KinematicRL,":[185],"consistently":[186],"improves":[187],"kinematic":[188],"performance":[189],"adapts":[191],"varying":[193],"number":[194],"detected":[196],"humans.":[197],"Experiments":[198],"in":[199],"environments":[201],"demonstrate":[202],"that,":[203],"when":[204],"combined":[205],"proposed":[208],"pipeline,":[210],"KinematicRL":[211],"can":[212],"be":[213],"deployed":[214],"on":[215],"real":[217],"minimal":[222],"modifications.":[223]},"counts_by_year":[],"updated_date":"2026-07-04T06:09:54.619538","created_date":"2026-06-16T00:00:00"}