{"id":"https://openalex.org/W7118146452","doi":"https://doi.org/10.1007/s11063-025-11821-2","title":"Reinforcement Learning-Based Intelligent Path Planning for Optimal Navigation in Dynamic Environments","display_name":"Reinforcement Learning-Based Intelligent Path Planning for Optimal Navigation in Dynamic Environments","publication_year":2026,"publication_date":"2026-01-04","ids":{"openalex":"https://openalex.org/W7118146452","doi":"https://doi.org/10.1007/s11063-025-11821-2","pmid":"https://pubmed.ncbi.nlm.nih.gov/41573146"},"language":"en","primary_location":{"id":"doi:10.1007/s11063-025-11821-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-025-11821-2","pdf_url":null,"source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s11063-025-11821-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121890600","display_name":"Anil Kumar Yadav","orcid":null},"institutions":[{"id":"https://openalex.org/I464993","display_name":"Barkatullah University","ror":"https://ror.org/02ax13658","country_code":"IN","type":"education","lineage":["https://openalex.org/I464993"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anil Kumar Yadav","raw_affiliation_strings":["VIT Bhopal University, Bhopal-Indore Highway, Bhopal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VIT Bhopal University, Bhopal-Indore Highway, Bhopal, India","institution_ids":["https://openalex.org/I464993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085414669","display_name":"Purushottam Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I155125381","display_name":"Galgotias University","ror":"https://ror.org/02w8ba206","country_code":"IN","type":"education","lineage":["https://openalex.org/I155125381"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Purushottam Sharma","raw_affiliation_strings":["School of Computer Science and Engineering, Galgotias University, Greater Noida, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Galgotias University, Greater Noida, India","institution_ids":["https://openalex.org/I155125381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102568279","display_name":"Xiaochun Cheng","orcid":"https://orcid.org/0000-0003-0371-9646"},"institutions":[{"id":"https://openalex.org/I39586589","display_name":"Swansea University","ror":"https://ror.org/053fq8t95","country_code":"GB","type":"education","lineage":["https://openalex.org/I39586589"]},{"id":"https://openalex.org/I4210113874","display_name":"Energy Safety Research Institute","ror":"https://ror.org/026znxe07","country_code":"GB","type":"facility","lineage":["https://openalex.org/I39586589","https://openalex.org/I4210113874"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaochun Cheng","raw_affiliation_strings":["Computer Science Department, Bay Campus Fabian Way, Swansea University, Swansea, SA1 8EN Wales UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Bay Campus Fabian Way, Swansea University, Swansea, SA1 8EN Wales UK","institution_ids":["https://openalex.org/I39586589","https://openalex.org/I4210113874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102811003","display_name":"Shiv Shankar Prasad Shukla","orcid":"https://orcid.org/0000-0003-3501-0500"},"institutions":[{"id":"https://openalex.org/I464993","display_name":"Barkatullah University","ror":"https://ror.org/02ax13658","country_code":"IN","type":"education","lineage":["https://openalex.org/I464993"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shiv Shankar Prasad Shukla","raw_affiliation_strings":["VIT Bhopal University, Bhopal-Indore Highway, Bhopal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VIT Bhopal University, Bhopal-Indore Highway, Bhopal, India","institution_ids":["https://openalex.org/I464993"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5085414669"],"corresponding_institution_ids":["https://openalex.org/I155125381"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":22.8522,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97198873,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"58","issue":"1","first_page":"10","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.7657999992370605,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.7657999992370605,"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":0.0608999989926815,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.014399999752640724,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8769000172615051},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.6665999889373779},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.6481000185012817},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.6467000246047974},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5972999930381775},{"id":"https://openalex.org/keywords/shortest-path-problem","display_name":"Shortest path problem","score":0.5758000016212463},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5248000025749207},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.5157999992370605},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5138999819755554},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4410000145435333}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8769000172615051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307999730110168},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.6665999889373779},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.6481000185012817},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.6467000246047974},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5972999930381775},{"id":"https://openalex.org/C22590252","wikidata":"https://www.wikidata.org/wiki/Q1058754","display_name":"Shortest path problem","level":3,"score":0.5758000016212463},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5248000025749207},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.5157999992370605},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44350001215934753},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4368000030517578},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4244999885559082},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.34630000591278076},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C173870130","wikidata":"https://www.wikidata.org/wiki/Q8548","display_name":"Dijkstra's algorithm","level":4,"score":0.3361000120639801},{"id":"https://openalex.org/C6180225","wikidata":"https://www.wikidata.org/wiki/Q3411771","display_name":"Penalty method","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2720000147819519},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C131806220","wikidata":"https://www.wikidata.org/wiki/Q852705","display_name":"Evaluation function","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s11063-025-11821-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-025-11821-2","pdf_url":null,"source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},{"id":"pmid:41573146","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41573146","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural processing letters","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12819461","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12819461/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Neural Process Lett","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s11063-025-11821-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-025-11821-2","pdf_url":null,"source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4826524555683136,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4382307673","display_name":null,"funder_award_id":"EP/W020408/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2917089854","https://openalex.org/W2970414985","https://openalex.org/W2970741249","https://openalex.org/W3092927864","https://openalex.org/W3100789280","https://openalex.org/W3120133279","https://openalex.org/W3136026272","https://openalex.org/W3149798409","https://openalex.org/W3153002900","https://openalex.org/W3166118626","https://openalex.org/W3206193482","https://openalex.org/W3207078867","https://openalex.org/W3208630584","https://openalex.org/W4213057498","https://openalex.org/W4213213759","https://openalex.org/W4224300633","https://openalex.org/W4283261583","https://openalex.org/W4286615890","https://openalex.org/W4319320505","https://openalex.org/W4388634858","https://openalex.org/W4392251565","https://openalex.org/W4401723520","https://openalex.org/W4401991753","https://openalex.org/W4407638441","https://openalex.org/W4414112501","https://openalex.org/W4415199179"],"related_works":[],"abstract_inverted_index":{"Path":[0],"selection":[1],"and":[2,14,50,81,184,201,225,234,255,288,305,312],"planning":[3],"are":[4],"crucial":[5],"for":[6,46,100,157,172],"autonomous":[7],"mobile":[8],"robots":[9],"(AMRs)":[10],"to":[11,23,126,134,144,180,261,280,318],"navigate":[12],"efficiently":[13],"avoid":[15],"obstacles.":[16],"Traditional":[17],"methods":[18],"rely":[19],"on":[20,112,117,168,230,315],"analytical":[21],"search":[22],"identify":[24],"the":[25,58,61,79,83,118,124,127,139,191,216,228,245,251,271],"shortest":[26,192],"distance.":[27,267],"However,":[28],"Reinforcement":[29],"learning":[30,96,284,297,314],"enhances":[31],"performance":[32],"by":[33,195,301],"optimizing":[34,169],"a":[35,259],"sequence":[36,48,120],"of":[37,63,121,253,273],"actions":[38,122],"efficiently.":[39],"It":[40],"is":[41,97],"an":[42,212],"iterative":[43],"approach":[44,131],"used":[45],"computational":[47],"modeling":[49],"dynamic":[51,101,107,158,205],"programming.":[52],"RL":[53,210],"received":[54],"sensory":[55],"input":[56],"from":[57,123],"environment":[59,98,140],"in":[60,93,106,175,204,264,291],"form":[62],"observation":[64],"or":[65,72,114,148],"state.":[66,129],"The":[67,187],"agent":[68],"interpreted":[69],"every":[70],"reward":[71,170,214,220,247],"penalty":[73],"through":[74],"trial-and-error":[75],"interaction.":[76],"Policy":[77],"maximizes":[78],"rewards":[80,113],"selects":[82],"optimal":[84,136],"action":[85],"among":[86],"all":[87],"possible":[88],"actions.":[89],"A":[90],"challenging":[91],"problem":[92],"traditional":[94],"reinforcement":[95,275,296],"generalization":[99],"systems.":[102,294],"Q-learning":[103,154],"faces":[104],"challenges":[105],"environments":[108],"because":[109],"it":[110,226],"relies":[111],"penalties":[115],"based":[116],"entire":[119],"start":[125],"end":[128],"This":[130],"often":[132],"fails":[133],"produce":[135],"results":[137,242,269],"when":[138],"changes":[141],"unexpectedly":[142],"due":[143],"state":[145,219],"transitions,":[146],"iterations,":[147],"blocked":[149],"routes.":[150],"Such":[151],"limitations":[152],"make":[153],"less":[155],"effective":[156,300],"path":[159,177,194,282],"planning.":[160],"To":[161],"overcome":[162],"these":[163],"challenges,":[164],"this":[165,209],"study":[166,217],"focuses":[167],"functions":[171],"efficient":[173],"navigation":[174,182,293],"RL-based":[176],"planning,":[178],"aiming":[179],"enhance":[181],"efficiency":[183],"obstacle":[185],"avoidance.":[186],"proposed":[188],"method":[189],"evaluates":[190,227],"decision":[193,289],"considering":[196],"total":[197],"steps,":[198,200],"counted":[199],"discount":[202],"rates":[203],"environments.":[206],"By":[207],"implementing":[208],"with":[211],"optimized":[213,246],"mechanism,":[215],"analyzes":[218],"values":[221],"across":[222],"different":[223],"environments,":[224],"effect":[229],"state-action":[231],"pair-based":[232],"Q-Learning":[233,239],"neural":[235],"networks":[236],"using":[237],"Deep":[238],"algorithms.":[240],"Here,":[241],"demonstrate":[243],"that":[244],"function":[248],"effectively":[249],"decreases":[250],"number":[252],"iterations":[254],"episodes":[256],"while":[257],"achieving":[258],"30%":[260],"70%":[262],"reduction":[263],"overall":[265],"trajectory":[266],"These":[268],"highlight":[270],"effectiveness":[272],"reward-based":[274],"learning,":[276],"demonstrating":[277],"its":[278],"potential":[279],"improve":[281],"optimization,":[283],"rate,":[285],"episode":[286],"completion,":[287],"accuracy":[290],"intelligent":[292],"Q-learning-based":[295],"becomes":[298],"more":[299],"combining":[302],"multiple":[303],"agents":[304],"utilizing":[306],"decision-making":[307],"techniques":[308],"such":[309],"as":[310],"federated":[311],"transfer":[313],"larger":[316],"maps":[317],"ensure":[319],"convergence.":[320]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-01-04T00:00:00"}