The Ohio State University, Columbus, OH 43210, USA
"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH 43210, USA
","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081375816","display_name":"Yunxiang Gan","orcid":"https://orcid.org/0009-0008-7568-9101","observed_orcids":["https://orcid.org/0009-0008-7568-9101"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunxiang Gan","raw_affiliation_strings":["Moloco, CA, USA
"],"raw_orcid":"https://orcid.org/0009-0008-7568-9101","affiliations":[{"raw_affiliation_string":"Moloco, CA, USA
","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017399618","display_name":"Shuguang Xiong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuguang Xiong","raw_affiliation_strings":["Microsoft Inc., Beijing 100080, China
"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Inc., Beijing 100080, China
","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0621,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77928074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"6","issue":"4","first_page":"51","last_page":"65"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8730000257492065,"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":0.8730000257492065,"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":0.07320000231266022,"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/T11814","display_name":"Advanced Manufacturing and Logistics Optimization","score":0.01850000023841858,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/path-planning","display_name":"path planning","score":0.6700000166893005},{"id":"https://openalex.org/keywords/spatial-attention-mechanism","display_name":"spatial attention mechanism","score":0.8849999904632568},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"obstacle avoidance","score":0.8069999814033508},{"id":"https://openalex.org/keywords/ddpg","display_name":"deep deterministic policy gradient","score":0.9779999852180481},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.8690000176429749},{"id":"https://openalex.org/keywords/end-to-end-learning","display_name":"end-to-end learning","score":0.7929999828338623},{"id":"https://openalex.org/keywords/robot-navigation","display_name":"robot navigation","score":0.5249999761581421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6179553866386414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49058881402015686},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48981377482414246},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.45003175735473633},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4121745228767395},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.33877599239349365}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.30564/jcsr.v6i4.7197","doi":"https://doi.org/10.30564/jcsr.v6i4.7197","is_oa":true,"landing_page_url":"https://doi.org/10.30564/jcsr.v6i4.7197","pdf_url":null,"source":{"id":"https://openalex.org/S4210237592","display_name":"Journal of Computer Science Research","issn_l":"2630-5151","issn":["2630-5151"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4360969247","host_organization_name":"Bilingual Publishing","host_organization_lineage":["https://openalex.org/P4360969247"],"host_organization_lineage_names":["Bilingual Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computer Science Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.30564/jcsr.v6i4.7197","doi":"https://doi.org/10.30564/jcsr.v6i4.7197","is_oa":true,"landing_page_url":"https://doi.org/10.30564/jcsr.v6i4.7197","pdf_url":null,"source":{"id":"https://openalex.org/S4210237592","display_name":"Journal of Computer Science Research","issn_l":"2630-5151","issn":["2630-5151"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4360969247","host_organization_name":"Bilingual Publishing","host_organization_lineage":["https://openalex.org/P4360969247"],"host_organization_lineage_names":["Bilingual Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computer Science Research","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.651199996471405}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4321369474","https://openalex.org/W4360585206","https://openalex.org/W2122871747","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756"],"abstract_inverted_index":{"In":[0],"modern":[1],"logistics":[2],"and":[3,18,31,45,62,67,76,88,130,140,152,206,212,250,274],"delivery":[4,8,23,90,105,180,231,281],"systems,":[5],"mobile":[6,103],"robot":[7,22,104,280],"systems":[9,24,106],"have":[10],"garnered":[11],"significant":[12],"attention":[13,117,134,259],"due":[14],"to":[15,51,53,84,177],"their":[16],"efficiency":[17,41,63],"flexibility.":[19],"However,":[20],"existing":[21],"still":[25],"face":[26],"numerous":[27],"challenges":[28],"in":[29,59,64,127,143,171,182],"complex":[30,86,144,183],"dynamically":[32,131],"changing":[33,55],"environments.":[34,184],"For":[35],"instance,":[36],"traditional":[37],"algorithms":[38],"exhibit":[39],"low":[40],"when":[42],"processing":[43],"high-dimensional":[44,172],"unstructured":[46],"data,":[47],"making":[48],"it":[49,80],"difficult":[50],"adapt":[52],"real-time":[54],"environments,":[56,145],"which":[57],"results":[58,218],"reduced":[60],"accuracy":[61,149,243],"path":[65,153,245],"planning":[66],"task":[68,247],"execution.":[69],"Additionally,":[70],"the":[71,120,128,133,148,156,191,204,214,221,226,230,242,257,262],"lack":[72],"of":[73,150,209,229,244,255,279],"effective":[74,179],"perception":[75],"decision-making":[77],"mechanisms":[78],"makes":[79],"challenging":[81],"for":[82,102,165,276],"robots":[83,136,176],"handle":[85],"scenarios":[87],"variable":[89],"demands.":[91],"To":[92],"address":[93],"these":[94],"issues,":[95],"this":[96,112],"paper":[97],"proposes":[98],"an":[99,187],"optimization":[100,189,278],"method":[101,223],"based":[107],"on":[108,124,237],"deep":[109,263],"learning.":[110],"Firstly,":[111],"study":[113],"introduces":[114],"a":[115],"spatial":[116,258],"mechanism":[118,260],"into":[119,199],"model.":[121],"By":[122],"focusing":[123],"key":[125,239],"areas":[126],"environment":[129],"adjusting":[132],"points,":[135],"can":[137,193],"better":[138],"recognize":[139],"avoid":[141],"obstacles":[142],"thus":[146],"improving":[147],"navigation":[151],"planning.":[154],"Secondly,":[155],"Deep":[157],"Deterministic":[158],"Policy":[159],"Gradient":[160],"(DDPG)":[161],"algorithm":[162,266],"is":[163],"employed":[164],"policy":[166,264],"optimization,":[167],"facilitating":[168],"efficient":[169],"learning":[170],"continuous":[173],"spaces,":[174],"enabling":[175],"learn":[178],"strategies":[181],"Finally,":[185],"through":[186],"end-to-end":[188],"approach,":[190],"system":[192,215,251],"directly":[194],"convert":[195],"sensor":[196],"data":[197],"inputs":[198],"control":[200],"command":[201],"outputs,":[202],"reducing":[203],"complexity":[205],"error":[207],"accumulation":[208],"intermediate":[210],"steps":[211],"simplifying":[213],"structure.":[216],"Experimental":[217],"demonstrate":[219],"that":[220],"proposed":[222],"significantly":[224],"enhances":[225],"overall":[227],"performance":[228],"system.":[232],"It":[233],"performs":[234],"exceptionally":[235],"well":[236],"several":[238],"indicators,":[240],"including":[241],"planning,":[246],"execution":[248],"efficiency,":[249],"robustness.":[252],"The":[253],"effectiveness":[254],"combining":[256],"with":[261],"gradient":[265],"has":[267],"been":[268],"fully":[269],"validated,":[270],"providing":[271],"new":[272],"insights":[273],"methods":[275],"future":[277],"systems.":[282]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-08T09:06:37.294493","created_date":"2025-10-10T00:00:00"}