{"id":"https://openalex.org/W3004011906","doi":"https://doi.org/10.1109/iros40897.2019.8967680","title":"Task-Motion Planning with Reinforcement Learning for Adaptable Mobile Service Robots","display_name":"Task-Motion Planning with Reinforcement Learning for Adaptable Mobile Service Robots","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3004011906","doi":"https://doi.org/10.1109/iros40897.2019.8967680","mag":"3004011906"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8967680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5032392594","display_name":"Yuqian Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuqian Jiang","raw_affiliation_strings":["University of Texas at Austin,Department of Computer Science,Austin,TX,USA","Department of Computer Science, University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Department of Computer Science,Austin,TX,USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564849","display_name":"Fangkai Yang","orcid":"https://orcid.org/0000-0002-3089-0345"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Fangkai Yang","raw_affiliation_strings":["NVIDIA Corporation,Redmond,WA,USA","NVIDIA Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation,Redmond,WA,USA","institution_ids":["https://openalex.org/I4210127875","https://openalex.org/I1304085615"]},{"raw_affiliation_string":"NVIDIA Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362573","display_name":"Shiqi Zhang","orcid":"https://orcid.org/0000-0003-4110-8213"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiqi Zhang","raw_affiliation_strings":["SUNY-Binghamton,Department of Computer Science,Binghamton,NY,USA","Department of Computer Science, SUNY-Binghamton, Binghamton, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SUNY-Binghamton,Department of Computer Science,Binghamton,NY,USA","institution_ids":["https://openalex.org/I123946342"]},{"raw_affiliation_string":"Department of Computer Science, SUNY-Binghamton, Binghamton, NY, USA","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001594330","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0002-6795-420X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Stone","raw_affiliation_strings":["University of Texas at Austin,Department of Computer Science,Austin,TX,USA","Department of Computer Science, University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Department of Computer Science,Austin,TX,USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0338,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.90018423,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"2019","issue":null,"first_page":"7529","last_page":"7534"},"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":0.9990000128746033,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9973999857902527,"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":0.8401696085929871},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7291249632835388},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.669281005859375},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6258189678192139},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5697984099388123},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5532057285308838},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.5068307518959045},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.48221004009246826},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4815993010997772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4601164162158966},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.4592227339744568},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.4494369924068451},{"id":"https://openalex.org/keywords/service-robot","display_name":"Service robot","score":0.4468819797039032},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.37036949396133423},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1631683111190796},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06978946924209595},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.06890237331390381},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06593441963195801}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8401696085929871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7291249632835388},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.669281005859375},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6258189678192139},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5697984099388123},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5532057285308838},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.5068307518959045},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.48221004009246826},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4815993010997772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4601164162158966},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.4592227339744568},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.4494369924068451},{"id":"https://openalex.org/C2776228582","wikidata":"https://www.wikidata.org/wiki/Q7455797","display_name":"Service robot","level":3,"score":0.4468819797039032},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.37036949396133423},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1631683111190796},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06978946924209595},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06890237331390381},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06593441963195801},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros40897.2019.8967680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"mag:3041120638","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002272273515881","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W131069610","https://openalex.org/W1539210606","https://openalex.org/W1597309017","https://openalex.org/W1605439581","https://openalex.org/W2070683816","https://openalex.org/W2101915445","https://openalex.org/W2128990851","https://openalex.org/W2141841102","https://openalex.org/W2143602574","https://openalex.org/W2145339207","https://openalex.org/W2158548602","https://openalex.org/W2167340365","https://openalex.org/W2170655684","https://openalex.org/W2268708260","https://openalex.org/W2490090381","https://openalex.org/W2518731509","https://openalex.org/W2586777479","https://openalex.org/W2807712944","https://openalex.org/W2899455150","https://openalex.org/W2901136733","https://openalex.org/W2963709735","https://openalex.org/W2973517119","https://openalex.org/W3104605181","https://openalex.org/W6605295560","https://openalex.org/W6683443546","https://openalex.org/W6684906258","https://openalex.org/W6693839119","https://openalex.org/W6752474190","https://openalex.org/W6756486208"],"related_works":["https://openalex.org/W4380590094","https://openalex.org/W2050548713","https://openalex.org/W3119736302","https://openalex.org/W3200041777","https://openalex.org/W4386464271","https://openalex.org/W2015961810","https://openalex.org/W2956606787","https://openalex.org/W4324119010","https://openalex.org/W3110652258","https://openalex.org/W2971758839"],"abstract_inverted_index":{"Task-motion":[0],"planning":[1,107,202],"(TMP)":[2],"addresses":[3],"the":[4,20,86,109,119,127,143,164,170,183],"problem":[5,87],"of":[6,78,88],"efficiently":[7],"generating":[8],"executable":[9],"and":[10,56,80,93,112,200],"low-cost":[11],"task":[12,201],"plans":[13,29],"in":[14,30,45,91,108,122,169,176,186],"a":[15,31,39,46,70,100,177],"discrete":[16,110],"space":[17,111],"such":[18],"that":[19,43],"(initially":[21],"unknown)":[22],"action":[23,115],"costs":[24,116],"are":[25],"determined":[26],"by":[27,105,118],"motion":[28,120],"corresponding":[32],"continuous":[33,123],"space.":[34,124],"A":[35],"task-motion":[36,103,137],"plan":[37,104],"for":[38],"mobile":[40,178],"service":[41,179],"robot":[42,97,128,180,184],"behaves":[44],"highly":[47],"dynamic":[48,92],"domain":[49,54,181,196],"can":[50,147,162],"be":[51,148],"sensitive":[52],"to":[53,59,84,133,142,152,194],"uncertainty":[55],"changes,":[57],"leading":[58],"suboptimal":[60],"behaviors":[61],"or":[62],"execution":[63],"failures.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68],"propose":[69],"novel":[71],"framework,":[72],"TMP-RL,":[73],"which":[74,156],"is":[75,174],"an":[76,187],"integration":[77],"TMP":[79,90,199],"reinforcement":[81],"learning":[82,165],"(RL),":[83],"solve":[85],"robust":[89],"uncertain":[94],"domains.":[95],"The":[96],"first":[98],"generates":[99],"low-cost,":[101],"feasible":[102],"iteratively":[106],"updating":[113],"relevant":[114],"evaluated":[117,175],"planner":[121],"During":[125],"execution,":[126],"learns":[129],"via":[130],"model-free":[131],"RL":[132,139],"further":[134],"improve":[135],"its":[136],"plans.":[138],"enables":[140],"adaptability":[141,193],"current":[144],"domain,":[145],"but":[146],"costly":[149],"with":[150],"regards":[151],"experience;":[153],"using":[154],"TMP,":[155],"does":[157],"not":[158],"rely":[159],"on":[160],"experience,":[161],"jump-start":[163],"process":[166],"before":[167],"executing":[168],"real":[171],"world.":[172],"TMP-RL":[173],"where":[182],"navigates":[185],"office":[188],"area,":[189],"showing":[190],"significantly":[191],"improved":[192],"unseen":[195],"dynamics":[197],"over":[198],"(TP)-RL":[203],"methods.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}