{"id":"https://openalex.org/W7225808928","doi":"https://doi.org/10.3390/app162211159","title":"Enhancing Path Planning with Self-Imitation and Intrinsic Curiosity in Soft Actor\u2013Critic","display_name":"Enhancing Path Planning with Self-Imitation and Intrinsic Curiosity in Soft Actor\u2013Critic","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225808928","doi":"https://doi.org/10.3390/app162211159"},"language":"en","primary_location":{"id":"doi:10.3390/app162211159","doi":"https://doi.org/10.3390/app162211159","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app162211159","pdf_url":null,"source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/app162211159","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133563099","display_name":"Xingyi Pan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210104252","display_name":"Air Force Engineering University","ror":"https://ror.org/00seraz22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyi Pan","raw_affiliation_strings":["Air Traffic Control and Navigation School, Air Force Engineering University, Xi\u2019an 710051, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Air Traffic Control and Navigation School, Air Force Engineering University, Xi\u2019an 710051, China","institution_ids":["https://openalex.org/I4210104252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126054672","display_name":"Xingyu He","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210104252","display_name":"Air Force Engineering University","ror":"https://ror.org/00seraz22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu He","raw_affiliation_strings":["Air Traffic Control and Navigation School, Air Force Engineering University, Xi\u2019an 710051, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Air Traffic Control and Navigation School, Air Force Engineering University, Xi\u2019an 710051, China","institution_ids":["https://openalex.org/I4210104252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091108887","display_name":"Xiaoyue Ren","orcid":"https://orcid.org/0009-0008-2703-3183","observed_orcids":["https://orcid.org/0009-0008-2703-3183"]},"institutions":[{"id":"https://openalex.org/I4210104252","display_name":"Air Force Engineering University","ror":"https://ror.org/00seraz22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyue Ren","raw_affiliation_strings":["Air Traffic Control and Navigation School, Air Force Engineering University, Xi\u2019an 710051, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Air Traffic Control and Navigation School, Air Force Engineering University, Xi\u2019an 710051, China","institution_ids":["https://openalex.org/I4210104252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047632342","display_name":"Duo Qi","orcid":"https://orcid.org/0000-0001-5254-6310","observed_orcids":["https://orcid.org/0000-0001-5254-6310"]},"institutions":[{"id":"https://openalex.org/I4210104252","display_name":"Air Force Engineering University","ror":"https://ror.org/00seraz22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Duo Qi","raw_affiliation_strings":["Air Traffic Control and Navigation School, Air Force Engineering University, Xi\u2019an 710051, China"],"raw_orcid":"https://orcid.org/0000-0001-5254-6310","affiliations":[{"raw_affiliation_string":"Air Traffic Control and Navigation School, Air Force Engineering University, Xi\u2019an 710051, China","institution_ids":["https://openalex.org/I4210104252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161431062","display_name":"Zhichao Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhichao Chen","raw_affiliation_strings":["Unit 95910, Jiuquan 735018, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unit 95910, Jiuquan 735018, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5158571512","display_name":"Tianyu Zheng","orcid":"https://orcid.org/0009-0004-5558-7619","observed_orcids":["https://orcid.org/0009-0004-5558-7619"]},"institutions":[{"id":"https://openalex.org/I4210104252","display_name":"Air Force Engineering University","ror":"https://ror.org/00seraz22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Zheng","raw_affiliation_strings":["Air Traffic Control and Navigation School, Air Force Engineering University, Xi\u2019an 710051, China"],"raw_orcid":"https://orcid.org/0009-0004-5558-7619","affiliations":[{"raw_affiliation_string":"Air Traffic Control and Navigation School, Air Force Engineering University, Xi\u2019an 710051, China","institution_ids":["https://openalex.org/I4210104252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5091108887"],"corresponding_institution_ids":["https://openalex.org/I4210104252"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2896},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2896},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"22","first_page":"11159","last_page":"11159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":9.999999747378752e-05,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0,"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":[],"concepts":[{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.6876000165939331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6301000118255615},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.6118000149726868},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5799999833106995},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.5083000063896179},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.5081999897956848},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4724000096321106},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.365200012922287},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.30730000138282776},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C129045301","wikidata":"https://www.wikidata.org/wiki/Q7144654","display_name":"Path length","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/app162211159","doi":"https://doi.org/10.3390/app162211159","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app162211159","pdf_url":null,"source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/app162211159","doi":"https://doi.org/10.3390/app162211159","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app162211159","pdf_url":null,"source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2039167866","https://openalex.org/W2150500908","https://openalex.org/W2734970688","https://openalex.org/W2917089854","https://openalex.org/W3037694644","https://openalex.org/W3088314378","https://openalex.org/W3092927864","https://openalex.org/W3168738617","https://openalex.org/W4210908354","https://openalex.org/W4285253626","https://openalex.org/W4327956071","https://openalex.org/W4387345340","https://openalex.org/W4389232926","https://openalex.org/W4400018492","https://openalex.org/W4408622702","https://openalex.org/W4411133030","https://openalex.org/W4412651267"],"related_works":[],"abstract_inverted_index":{"The":[0,267,391],"integration":[1],"of":[2,23,175,187,288,302,344,376,419],"unmanned":[3],"aerial":[4],"vehicles":[5],"(UAVs)":[6],"into":[7],"low-altitude":[8],"urban":[9,25,224],"airspace":[10,498],"for":[11,457],"parcel":[12],"delivery":[13,150],"and":[14,42,47,76,102,182,202,238,293,323,363,384,412,423,433,453,504],"last-mile":[15],"logistics":[16],"is":[17,38,65,121,164,206,255,261,370,389,393,477],"emerging":[18],"as":[19,464,466],"a":[20,54,77,103,108,138,193,221,272,396,438,450,467,489],"key":[21],"component":[22,354,358],"future":[24],"air":[26],"mobility,":[27],"yet":[28],"its":[29,59,312],"operational":[30,511],"viability":[31],"depends":[32],"on":[33,116],"autonomous":[34],"path":[35,225],"planning":[36,56,226],"that":[37],"simultaneously":[39],"safe,":[40],"reliable,":[41],"efficient":[43],"under":[44,212],"dense":[45],"obstacles":[46],"limited":[48],"sensing.":[49],"Deep":[50],"reinforcement":[51],"learning":[52,100,156],"offers":[53],"promising":[55],"paradigm,":[57],"but":[58],"deployment":[60,512],"in":[61,220,271,316,395,437,484,496],"this":[62,86,442],"transport":[63],"setting":[64],"severely":[66],"constrained":[67],"by":[68],"sparse":[69,213],"task-level":[70],"success":[71,214,284,314,350,361,451],"signals,":[72],"low":[73],"sample":[74],"efficiency,":[75],"poorly":[78],"regulated":[79],"exploration\u2013exploitation":[80],"trade-off.":[81],"To":[82],"address":[83],"these":[84],"issues,":[85],"paper":[87],"proposes":[88],"an":[89],"improved":[90],"Soft":[91],"Actor\u2013Critic":[92],"(SAC)":[93],"algorithm":[94],"named":[95],"SIL-CAT-SAC,":[96],"which":[97],"integrates":[98],"self-imitation":[99,155],"(SIL)":[101],"curiosity-adaptive":[104],"temperature":[105,136],"mechanism.":[106],"Specifically,":[107],"curiosity-augmented":[109],"target":[110],"entropy":[111],"adjustment":[112],"(CAT)":[113],"module":[114],"based":[115],"enhanced":[117],"random":[118],"network":[119],"distillation":[120],"designed":[122],"to":[123,130,166,208,428,479,488],"dynamically":[124],"regulate":[125],"the":[126,149,173,185,251,257,265,277,282,289,294,299,306,326,332,339,345,349,353,360,367,374,377,417,420,426,447,458,472,475,480],"exploration":[127],"intensity":[128],"according":[129],"state":[131],"novelty,":[132],"achieving":[133],"instance-level":[134],"adaptive":[135],"control;":[137],"linearly":[139],"annealed":[140],"curiosity":[141],"coefficient":[142],"further":[143],"prevents":[144],"intrinsic":[145],"rewards":[146],"from":[147,178],"overriding":[148],"objective":[151],"near":[152],"convergence.":[153],"A":[154,335],"auxiliary":[157],"loss":[158],"combined":[159],"with":[160,264,400,499],"prioritized":[161],"experience":[162,180],"replay":[163,181],"introduced":[165],"selectively":[167],"amplify":[168],"genuine":[169],"successful":[170],"trajectories,":[171],"eliminating":[172],"interference":[174],"pseudo-success":[176],"samples":[177],"hindsight":[179],"markedly":[183],"improving":[184],"utilization":[186],"rare":[188],"positive":[189,386,491],"samples.":[190],"In":[191],"addition,":[192],"continuous":[194],"reward":[195],"function":[196],"incorporating":[197],"distance":[198],"increment,":[199],"potential":[200],"shaping,":[201],"obstacle":[203,230,291],"warning":[204],"terms":[205],"constructed":[207],"alleviate":[209],"gradient":[210],"vanishing":[211],"feedback.":[215],"Comprehensive":[216],"experiments":[217,424],"are":[218,243,415,431],"conducted":[219,394],"35\u00d735":[222],"grid-based":[223,398,445],"environment":[227],"across":[228,253],"three":[229,246,290,333],"densities,":[231,292],"against":[232,276],"two":[233,307,481],"state-of-the-art":[234],"SAC":[235],"variants,":[236],"REDQ":[237],"M-SAC.":[239],"All":[240],"reported":[241,262,436],"metrics":[242],"averaged":[244],"over":[245],"independent":[247],"training":[248,318],"seeds;":[249],"where":[250,342],"dispersion":[252],"seeds":[254],"meaningful,":[256],"cross-seed":[258],"standard":[259],"deviation":[260],"together":[263],"mean.":[266],"results":[268,448],"show":[269],"that,":[270],"frozen":[273],"policy":[274],"evaluation":[275],"fixed":[278],"goal,":[279],"SIL-CAT-SAC":[280],"attains":[281],"highest":[283],"rate":[285,362,452],"at":[286,305,338,461,471],"each":[287],"exact":[295],"Friedman":[296],"test":[297],"rejects":[298],"null":[300],"hypothesis":[301],"equal":[303],"performance":[304],"higher":[308],"densities.":[309],"It":[310],"reaches":[311,348],"operating":[313],"level":[315],"fewer":[317],"episodes":[319],"than":[320,373,487],"either":[321,357],"baseline,":[322],"it":[324],"exhibits":[325],"largest":[327],"average":[328],"robustness":[329,469],"index":[330],"among":[331],"algorithms.":[334],"factorial":[336],"ablation":[337],"lowest":[340],"density,":[341,463],"none":[343],"four":[346],"configurations":[347],"ceiling,":[351],"separates":[352],"combinations:":[355],"removing":[356],"lowers":[359],"delays":[364],"convergence,":[365],"while":[366],"joint":[368],"effect":[369],"no":[371,385],"larger":[372],"sum":[375],"individual":[378],"effects,":[379],"so":[380],"both":[381],"components":[382,482],"contribute":[383],"CAT-SIL":[387],"interaction":[388,492],"claimed.":[390,515],"study":[392],"two-dimensional":[397,444],"abstraction":[399],"static":[401],"obstacles;":[402],"three-dimensional":[403,429,497],"flight":[404],"dynamics,":[405],"dynamic":[406,500],"obstacles,":[407,501],"wind":[408],"disturbance,":[409],"sensing":[410],"uncertainty,":[411,503],"communication":[413],"constraints":[414],"outside":[416],"scope":[418],"present":[421],"evaluation,":[422],"extending":[425],"framework":[427],"environments":[430],"underway":[432],"will":[434],"be":[435,514],"follow-up":[439],"paper.":[440],"Within":[441],"simulated":[443],"setting,":[446],"support":[449],"convergence":[454],"efficiency":[455],"advantage":[456,470,476],"proposed":[459],"method":[460],"every":[462],"well":[465],"cross-density":[468],"intermediate":[473],"density;":[474],"attributed":[478],"acting":[483],"combination":[485],"rather":[486],"demonstrated":[490],"between":[493],"them.":[494],"Validation":[495],"sensor":[502],"realistic":[505],"vehicle":[506],"dynamics":[507],"remains":[508],"necessary":[509],"before":[510],"can":[513]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}