{"id":"https://openalex.org/W2047746192","doi":"https://doi.org/10.2316/journal.206.2016.4.206-4255","title":"RSMDP-BASED ROBUST Q-LEARNING FOR OPTIMAL PATH PLANNING IN A DYNAMIC ENVIRONMENT","display_name":"RSMDP-BASED ROBUST Q-LEARNING FOR OPTIMAL PATH PLANNING IN A DYNAMIC ENVIRONMENT","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2047746192","doi":"https://doi.org/10.2316/journal.206.2016.4.206-4255","mag":"2047746192"},"language":"en","primary_location":{"id":"doi:10.2316/journal.206.2016.4.206-4255","is_oa":false,"landing_page_url":"https://doi.org/10.2316/journal.206.2016.4.206-4255","pdf_url":null,"source":{"id":"https://openalex.org/S74998426","display_name":"International Journal of Robotics and Automation","issn_l":"0826-8185","issn":["0826-8185","1925-7090"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Robotics and Automation","raw_type":"journal-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/A5100613465","display_name":"Yunfei Zhang","orcid":"https://orcid.org/0000-0001-8160-7995"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Yunfei Zhang","raw_affiliation_strings":["University of British Columbia"],"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100690569","display_name":"Weilin Li","orcid":"https://orcid.org/0000-0003-0345-4713"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weilin Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077953037","display_name":"Clarence W. de Silva","orcid":"https://orcid.org/0000-0002-5871-639X"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Clarence W. de Silva","raw_affiliation_strings":["University of British Columbia"],"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100613465"],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":0.668,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75553393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"31","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":1.0,"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":1.0,"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":0.9961000084877014,"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/T10142","display_name":"Formal Methods in Verification","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.805649995803833},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.7767317891120911},{"id":"https://openalex.org/keywords/probabilistic-roadmap","display_name":"Probabilistic roadmap","score":0.7452673316001892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6970455050468445},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.6868121027946472},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5737336874008179},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.5724032521247864},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5664774179458618},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5412584543228149},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.5098735094070435},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4759937524795532},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.46774178743362427},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4479656517505646},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4353167712688446},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4285229742527008},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.42790886759757996},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.39745962619781494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38323524594306946},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.2734021544456482},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1869901418685913},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1461818516254425}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.805649995803833},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.7767317891120911},{"id":"https://openalex.org/C2778803389","wikidata":"https://www.wikidata.org/wiki/Q7246866","display_name":"Probabilistic roadmap","level":4,"score":0.7452673316001892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6970455050468445},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.6868121027946472},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5737336874008179},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.5724032521247864},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5664774179458618},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5412584543228149},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.5098735094070435},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4759937524795532},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.46774178743362427},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4479656517505646},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4353167712688446},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4285229742527008},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.42790886759757996},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.39745962619781494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38323524594306946},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2734021544456482},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1869901418685913},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1461818516254425},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2316/journal.206.2016.4.206-4255","is_oa":false,"landing_page_url":"https://doi.org/10.2316/journal.206.2016.4.206-4255","pdf_url":null,"source":{"id":"https://openalex.org/S74998426","display_name":"International Journal of Robotics and Automation","issn_l":"0826-8185","issn":["0826-8185","1925-7090"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Robotics and Automation","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W123646622","https://openalex.org/W1509235676","https://openalex.org/W1521785144","https://openalex.org/W1756618330","https://openalex.org/W1977972789","https://openalex.org/W1979189365","https://openalex.org/W2017646611","https://openalex.org/W2032647198","https://openalex.org/W2055207897","https://openalex.org/W2061412229","https://openalex.org/W2096636360","https://openalex.org/W2103120971","https://openalex.org/W2111112078","https://openalex.org/W2112271657","https://openalex.org/W2113122194","https://openalex.org/W2113286054","https://openalex.org/W2113778071","https://openalex.org/W2121863487","https://openalex.org/W2126626010","https://openalex.org/W2128990851","https://openalex.org/W2138071745","https://openalex.org/W2146467128","https://openalex.org/W2152536965","https://openalex.org/W2155974215","https://openalex.org/W2171393685","https://openalex.org/W2611243847"],"related_works":["https://openalex.org/W2060743914","https://openalex.org/W2808418668","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W4380550992","https://openalex.org/W4322760752","https://openalex.org/W3096874164","https://openalex.org/W4223607701","https://openalex.org/W2970347269","https://openalex.org/W2146763310"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"arobust":[3],"Q-learning":[4,158],"method":[5,13,63],"for":[6,56,85,100],"path":[7,84,155],"planningin":[8],"a":[9,19,33,46,52,143],"dynamic":[10,30,65],"environment.":[11],"The":[12,122,137,149],"consists":[14],"of":[15,71,118,129],"three":[16],"steps:":[17],"first,":[18],"regime-switching":[20],"Markov":[21],"decision":[22],"process":[23],"(RSMDP)":[24],"is":[25,37,75,94,134,140,159],"formed":[26],"to":[27,51,80,96,142,165],"present":[28],"the":[29,41,57,72,78,87,92,116,119,127,153,166],"environment;":[31],"second":[32],"probabilistic":[34],"roadmap":[35],"(PRM)":[36],"constructed,":[38],"integrated":[39,76],"with":[40,64,77,131,157],"RSMDP":[42],"and":[43,59,162],"stored":[44],"as":[45],"graph":[47],"whose":[48],"nodes":[49],"correspond":[50],"collision-free":[53],"world":[54],"state":[55],"robot;":[58],"third,":[60],"an":[61,82],"onlineQ-learning":[62],"stepsize,":[66],"which":[67],"facilitates":[68],"robust":[69],"convergence":[70],"Q-value":[73],"iteration,":[74],"PRM":[79],"determine":[81],"optimal":[83],"reaching":[86],"goal.":[88],"In":[89],"this":[90],"manner,":[91],"robot":[93,145],"able":[95,160],"use":[97,123],"past":[98],"experience":[99],"improving":[101],"its":[102],"performance":[103],"in":[104,126,146],"avoiding":[105],"not":[106],"only":[107],"static":[108],"obstacles":[109,130],"but":[110],"also":[111],"moving":[112],"obstacles,":[113],"without":[114],"knowing":[115],"nature":[117],"obstacle":[120],"motion.":[121],"ofregime":[124],"switching":[125],"avoidance":[128],"unknown":[132],"motion":[133],"particularly":[135],"innovative.\u00a0":[136],"developed":[138],"approach":[139],"applied":[141],"homecare":[144],"computer":[147],"simulation.":[148],"results":[150],"show":[151],"that":[152],"online":[154],"planner":[156],"torapidly":[161],"successfully":[163],"converge":[164],"correct":[167],"path.":[168]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}