{"id":"https://openalex.org/W4402353641","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651449","title":"A Method of Path Planning and Intelligent Exploration for Robot Based on Deep Reinforcement Learning","display_name":"A Method of Path Planning and Intelligent Exploration for Robot Based on Deep Reinforcement Learning","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402353641","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651449"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10651449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5107119918","display_name":"Xianglin Lyu","orcid":null},"institutions":[{"id":"https://openalex.org/I161350542","display_name":"China Three Gorges University","ror":"https://ror.org/0419nfc77","country_code":"CN","type":"education","lineage":["https://openalex.org/I161350542"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xianglin Lyu","raw_affiliation_strings":["China Three Gorges University,Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering,Yichang,China"],"affiliations":[{"raw_affiliation_string":"China Three Gorges University,Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering,Yichang,China","institution_ids":["https://openalex.org/I161350542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088843034","display_name":"Zhaoxiang Zang","orcid":"https://orcid.org/0000-0002-6992-8419"},"institutions":[{"id":"https://openalex.org/I161350542","display_name":"China Three Gorges University","ror":"https://ror.org/0419nfc77","country_code":"CN","type":"education","lineage":["https://openalex.org/I161350542"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoxiang Zang","raw_affiliation_strings":["China Three Gorges University,Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering,Yichang,China"],"affiliations":[{"raw_affiliation_string":"China Three Gorges University,Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering,Yichang,China","institution_ids":["https://openalex.org/I161350542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008798822","display_name":"Sibo Li","orcid":"https://orcid.org/0000-0002-1705-844X"},"institutions":[{"id":"https://openalex.org/I161350542","display_name":"China Three Gorges University","ror":"https://ror.org/0419nfc77","country_code":"CN","type":"education","lineage":["https://openalex.org/I161350542"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sibo Li","raw_affiliation_strings":["China Three Gorges University,Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering,Yichang,China"],"affiliations":[{"raw_affiliation_string":"China Three Gorges University,Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering,Yichang,China","institution_ids":["https://openalex.org/I161350542"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107119918"],"corresponding_institution_ids":["https://openalex.org/I161350542"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53223737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9965000152587891,"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/T11615","display_name":"Control and Dynamics of Mobile Robots","score":0.9850999712944031,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8751389384269714},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.7353919148445129},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7322252988815308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5682754516601562},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5382383465766907},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.519071638584137},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4683759808540344},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.46292567253112793},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3488086760044098},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.053108274936676025}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8751389384269714},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.7353919148445129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322252988815308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5682754516601562},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5382383465766907},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.519071638584137},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4683759808540344},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.46292567253112793},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3488086760044098},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.053108274936676025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10651449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":29,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W2145339207","https://openalex.org/W2250297846","https://openalex.org/W2781726626","https://openalex.org/W2801441281","https://openalex.org/W2913668833","https://openalex.org/W2963523627","https://openalex.org/W2981038142","https://openalex.org/W2981260474","https://openalex.org/W2982316857","https://openalex.org/W2984557458","https://openalex.org/W2996196709","https://openalex.org/W2996896271","https://openalex.org/W3005657850","https://openalex.org/W3014101816","https://openalex.org/W3044051321","https://openalex.org/W3158260269","https://openalex.org/W3169154538","https://openalex.org/W4200140111","https://openalex.org/W4220902589","https://openalex.org/W4283773973","https://openalex.org/W4293144426","https://openalex.org/W6628764021","https://openalex.org/W6638018090","https://openalex.org/W6677939520","https://openalex.org/W6687681856","https://openalex.org/W6748638692","https://openalex.org/W6751540476","https://openalex.org/W6756303580"],"related_works":["https://openalex.org/W1904098742","https://openalex.org/W3158921809","https://openalex.org/W2161428574","https://openalex.org/W2077416514","https://openalex.org/W2618632915","https://openalex.org/W2359600231","https://openalex.org/W4292862729","https://openalex.org/W2380019117","https://openalex.org/W2150982344","https://openalex.org/W2157678966"],"abstract_inverted_index":{"The":[0,62,110,153],"field":[1],"of":[2,161,177],"path":[3,139],"planning":[4],"and":[5,27,88,115,142,147,193],"intelligent":[6,60],"exploration":[7,68,76,108,140,165,196],"for":[8,202],"robots":[9,19],"based":[10],"on":[11,150],"reinforcement":[12,46],"learning":[13,47,57,91],"consistently":[14],"garners":[15],"widespread":[16],"interest.":[17],"However,":[18],"often":[20],"encounter":[21],"challenges":[22],"such":[23],"as":[24],"sparse":[25],"rewards":[26],"incomplete":[28],"information":[29,188],"during":[30],"environmental":[31],"exploration,":[32],"complicating":[33],"the":[34,75,98,118,126,132,137,151,157,181],"task":[35],"at":[36,198],"hand.":[37],"This":[38],"paper":[39],"aims":[40],"to":[41,58,70,84,92,106,135],"introduce":[42],"a":[43,66,101,172,199],"novel":[44],"deep":[45],"algorithmic":[48],"approach":[49],"that":[50,156],"integrates":[51],"random":[52],"network":[53,104],"distillation":[54],"with":[55],"self-imitation":[56,90],"enhance":[59],"exploration.":[61,204],"proposed":[63],"algorithm":[64,99,158,182],"uses":[65],"curiosity-driven":[67],"mechanism":[69],"generate":[71],"experience":[72,82],"data":[73],"throughout":[74],"process.":[77],"Then,":[78],"it":[79],"employs":[80],"prioritized":[81],"replay":[83],"select":[85],"high-quality":[86],"samples":[87],"utilizes":[89],"imitate":[93],"optimal":[94],"sequence":[95],"trajectories.":[96],"Concurrently,":[97],"updates":[100],"new":[102],"policy":[103,111],"designed":[105],"guide":[107],"behavior.":[109],"is":[112,159],"further":[113],"updated":[114],"refined":[116],"through":[117],"Proximal":[119],"Policy":[120],"Optimization":[121],"(PPO)":[122],"algorithm.":[123,152],"To":[124],"validate":[125],"algorithm\u2019s":[127],"effectiveness,":[128],"we":[129],"have":[130,143],"employed":[131],"Minigrid":[133],"environment":[134],"simulate":[136],"robot\u2019s":[138],"endeavors":[141],"conducted":[144],"both":[145],"ablation":[146],"comparative":[148],"studies":[149],"findings":[154],"reveal":[155],"capable":[160],"accomplishing":[162],"more":[163],"complex":[164],"tasks":[166],"within":[167,189],"partially":[168,190],"observable":[169,191],"environments,":[170],"demonstrating":[171],"significant":[173],"advantage":[174],"in":[175,185],"terms":[176],"convergence":[178],"speed.":[179],"Consequently,":[180],"proves":[183],"effective":[184],"acquiring":[186],"valuable":[187],"settings":[192],"obtaining":[194],"superior":[195],"pathways":[197],"small":[200],"cost":[201],"robot":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}