{"id":"https://openalex.org/W2936135090","doi":"https://doi.org/10.1109/ccis.2018.8691217","title":"Reinforcement Learning for Robot Navigation in Nondeterministic Environments","display_name":"Reinforcement Learning for Robot Navigation in Nondeterministic Environments","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2936135090","doi":"https://doi.org/10.1109/ccis.2018.8691217","mag":"2936135090"},"language":"en","primary_location":{"id":"doi:10.1109/ccis.2018.8691217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccis.2018.8691217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)","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/A5100776309","display_name":"Xiaoyun Liu","orcid":"https://orcid.org/0000-0001-7083-5263"},"institutions":[{"id":"https://openalex.org/I194716290","display_name":"China Academy of Space Technology","ror":"https://ror.org/025397a59","country_code":"CN","type":"government","lineage":["https://openalex.org/I194716290","https://openalex.org/I2802615301"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyun Liu","raw_affiliation_strings":["Qian Xuesen Laboratory of Space Technology, Beijing 100094, China"],"affiliations":[{"raw_affiliation_string":"Qian Xuesen Laboratory of Space Technology, Beijing 100094, China","institution_ids":["https://openalex.org/I194716290"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011624128","display_name":"Qingrui Zhou","orcid":"https://orcid.org/0000-0002-3021-1891"},"institutions":[{"id":"https://openalex.org/I194716290","display_name":"China Academy of Space Technology","ror":"https://ror.org/025397a59","country_code":"CN","type":"government","lineage":["https://openalex.org/I194716290","https://openalex.org/I2802615301"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingrui Zhou","raw_affiliation_strings":["Qian Xuesen Laboratory of Space Technology, Beijing 100094, China"],"affiliations":[{"raw_affiliation_string":"Qian Xuesen Laboratory of Space Technology, Beijing 100094, China","institution_ids":["https://openalex.org/I194716290"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007612928","display_name":"Hailin Ren","orcid":"https://orcid.org/0000-0002-3944-9185"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hailin Ren","raw_affiliation_strings":["Department of Mechanical Engineering, Virginia Tech, Blacksburg, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101786001","display_name":"Changhao Sun","orcid":"https://orcid.org/0000-0002-2262-969X"},"institutions":[{"id":"https://openalex.org/I194716290","display_name":"China Academy of Space Technology","ror":"https://ror.org/025397a59","country_code":"CN","type":"government","lineage":["https://openalex.org/I194716290","https://openalex.org/I2802615301"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhao Sun","raw_affiliation_strings":["Qian Xuesen Laboratory of Space Technology, Beijing 100094, China"],"affiliations":[{"raw_affiliation_string":"Qian Xuesen Laboratory of Space Technology, Beijing 100094, China","institution_ids":["https://openalex.org/I194716290"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100776309"],"corresponding_institution_ids":["https://openalex.org/I194716290"],"apc_list":null,"apc_paid":null,"fwci":0.9772,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82729853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"615","last_page":"619"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12288","display_name":"Optimization and Search Problems","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/markov-decision-process","display_name":"Markov decision process","score":0.8050658702850342},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.788744330406189},{"id":"https://openalex.org/keywords/nondeterministic-algorithm","display_name":"Nondeterministic algorithm","score":0.7794449925422668},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.7002772092819214},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7001098990440369},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6234729290008545},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6212711930274963},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5938673615455627},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.57138592004776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5431252717971802},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5137354135513306},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4808264970779419},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4267197847366333},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4262283146381378},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.27414295077323914},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17955482006072998}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8050658702850342},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.788744330406189},{"id":"https://openalex.org/C176181172","wikidata":"https://www.wikidata.org/wiki/Q3490301","display_name":"Nondeterministic algorithm","level":2,"score":0.7794449925422668},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.7002772092819214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7001098990440369},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6234729290008545},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6212711930274963},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5938673615455627},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.57138592004776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5431252717971802},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5137354135513306},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4808264970779419},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4267197847366333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4262283146381378},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27414295077323914},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17955482006072998},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccis.2018.8691217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccis.2018.8691217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1681019253","https://openalex.org/W1979266466","https://openalex.org/W2060794637","https://openalex.org/W2089108971","https://openalex.org/W2121863487","https://openalex.org/W2154645004","https://openalex.org/W2157813244","https://openalex.org/W2295252581","https://openalex.org/W2486588043","https://openalex.org/W2783967294","https://openalex.org/W2963544079","https://openalex.org/W2996195849","https://openalex.org/W4301630257","https://openalex.org/W6689723076","https://openalex.org/W6722389926","https://openalex.org/W6747984218"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W3096874164","https://openalex.org/W4281812492","https://openalex.org/W3105579180","https://openalex.org/W2970347269","https://openalex.org/W2146763310","https://openalex.org/W3167472281","https://openalex.org/W4400868993"],"abstract_inverted_index":{"Mobile":[0],"robots":[1],"are":[2],"commonly":[3],"used":[4],"for":[5],"missions":[6],"like":[7],"target":[8],"searching":[9],"and":[10,47,63,74],"security":[11],"surveillance":[12],"in":[13,37,54,115],"unknown":[14,38],"environments,":[15],"where":[16],"an":[17],"exact":[18],"mathematical":[19],"model":[20],"may":[21],"not":[22],"be":[23],"available.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"formulate":[29],"the":[30,56,68,71,76,82,89,92,101,106,111,125],"problem":[31],"of":[32,70,81,91,124],"mobile":[33],"robot":[34],"path":[35,108],"planning":[36],"environments":[39,116],"as":[40],"a":[41,49,60],"nondeterministic":[42,118],"Markov":[43],"Decision":[44],"Process":[45],"(MDP),":[46],"provide":[48],"model-free":[50],"reinforcement":[51],"learning":[52,77,96],"solution":[53],"which":[55],"modified":[57],"Q-learning":[58,84],"utilizes":[59],"combined":[61],"\u03b5-greedy":[62],"Boltzmann":[64],"exploration.":[65],"We":[66,86],"simulate":[67],"validity":[69],"proposed":[72,102],"algorithm,":[73],"compare":[75],"process":[78],"with":[79],"that":[80,100,109],"original":[83],"algorithm.":[85],"also":[87],"analyze":[88],"effects":[90],"discounted":[93,126],"factor":[94],"on":[95],"results.":[97],"Simulations":[98],"show":[99],"algorithm":[103],"can":[104],"generate":[105],"shortest":[107],"obtains":[110],"maximized":[112],"accumulated":[113],"reward":[114],"having":[117],"Markovian":[119],"property":[120],"given":[121],"appropriate":[122],"values":[123],"factor.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}