{"id":"https://openalex.org/W2764297211","doi":"https://doi.org/10.1109/icra.2018.8461096","title":"PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-Based Planning","display_name":"PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-Based Planning","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2764297211","doi":"https://doi.org/10.1109/icra.2018.8461096","mag":"2764297211"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2018.8461096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1710.03937","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002971435","display_name":"Aleksandra Faust","orcid":"https://orcid.org/0000-0002-3268-8685"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aleksandra Faust","raw_affiliation_strings":["Google Brain, Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"Google Brain, Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033234426","display_name":"Kenneth Oslund","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenneth Oslund","raw_affiliation_strings":["Google Brain, Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"Google Brain, Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066139735","display_name":"\u00d3scar Ram\u00edrez","orcid":"https://orcid.org/0000-0002-9486-0129"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oscar Ramirez","raw_affiliation_strings":["Google Brain, Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"Google Brain, Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043268931","display_name":"Anthony Francis","orcid":"https://orcid.org/0000-0001-7772-7601"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Francis","raw_affiliation_strings":["Google Brain, Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"Google Brain, Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060753774","display_name":"Lydia Tapia","orcid":"https://orcid.org/0000-0002-7822-7091"},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lydia Tapia","raw_affiliation_strings":["Department of Computer Science, University of New Mexico, Albuquerque, NM"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of New Mexico, Albuquerque, NM","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004095912","display_name":"Marek Fi\u0161er","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marek Fiser","raw_affiliation_strings":["Google Brain, Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"Google Brain, Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021713982","display_name":"James Davidson","orcid":"https://orcid.org/0000-0001-5853-4310"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Davidson","raw_affiliation_strings":["Google Brain, Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"Google Brain, Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5002971435"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.4892,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.86714414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5113","last_page":"5120"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8292213678359985},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7258338928222656},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.6923980712890625},{"id":"https://openalex.org/keywords/probabilistic-roadmap","display_name":"Probabilistic roadmap","score":0.657350480556488},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5745787024497986},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5744870901107788},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5368410348892212},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4519850015640259},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.42385134100914},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4224443733692169},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.36811864376068115},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.33776581287384033},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.23498496413230896},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1421181559562683}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8292213678359985},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7258338928222656},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.6923980712890625},{"id":"https://openalex.org/C2778803389","wikidata":"https://www.wikidata.org/wiki/Q7246866","display_name":"Probabilistic roadmap","level":4,"score":0.657350480556488},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5745787024497986},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5744870901107788},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5368410348892212},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4519850015640259},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.42385134100914},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4224443733692169},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36811864376068115},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.33776581287384033},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.23498496413230896},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1421181559562683},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra.2018.8461096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1710.03937","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.03937","pdf_url":"https://arxiv.org/pdf/1710.03937","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2764297211","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1710.03937.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1710.03937","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1710.03937","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1710.03937","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.03937","pdf_url":"https://arxiv.org/pdf/1710.03937","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1424654272","https://openalex.org/W1540465515","https://openalex.org/W1631623342","https://openalex.org/W1756618330","https://openalex.org/W1977655452","https://openalex.org/W2000643286","https://openalex.org/W2010764164","https://openalex.org/W2024591926","https://openalex.org/W2029372064","https://openalex.org/W2036016432","https://openalex.org/W2050129189","https://openalex.org/W2067349577","https://openalex.org/W2073097405","https://openalex.org/W2108886361","https://openalex.org/W2111978237","https://openalex.org/W2119112357","https://openalex.org/W2128990851","https://openalex.org/W2141664020","https://openalex.org/W2145339207","https://openalex.org/W2149780310","https://openalex.org/W2168992242","https://openalex.org/W2173248099","https://openalex.org/W2186241545","https://openalex.org/W2201570790","https://openalex.org/W2299638491","https://openalex.org/W2443711627","https://openalex.org/W2529658650","https://openalex.org/W2611243847","https://openalex.org/W2953248129","https://openalex.org/W2964161785","https://openalex.org/W3104753760","https://openalex.org/W6632277873","https://openalex.org/W6632959618","https://openalex.org/W6657565755","https://openalex.org/W6667306072","https://openalex.org/W6676020571","https://openalex.org/W6684921986","https://openalex.org/W6694869790","https://openalex.org/W6727962482","https://openalex.org/W6756260461"],"related_works":["https://openalex.org/W2962917939","https://openalex.org/W3016507688","https://openalex.org/W3154227779","https://openalex.org/W3206901743","https://openalex.org/W2901421858","https://openalex.org/W3205663827","https://openalex.org/W3137207733","https://openalex.org/W2057933286","https://openalex.org/W3132983671","https://openalex.org/W3204789572","https://openalex.org/W2979712929","https://openalex.org/W2768523414","https://openalex.org/W3094789747","https://openalex.org/W3032985159","https://openalex.org/W2948271667","https://openalex.org/W92865624","https://openalex.org/W3092150668","https://openalex.org/W3088506193","https://openalex.org/W3207399992","https://openalex.org/W2532895062"],"abstract_inverted_index":{"We":[0,79,107],"present":[1],"PRM-RL,":[2,109],"a":[3],"hierarchical":[4],"method":[5],"for":[6,85],"long-range":[7,77],"navigation":[8,26,117,127,163],"task":[9,33,147,191],"completion":[10,148],"that":[11,28,51],"combines":[12],"sampling-based":[13,43,87,158],"path":[14],"planning":[15],"with":[16,119,138],"reinforcement":[17],"learning":[18],"(RL).":[19],"The":[20,60,89],"RL":[21,58,62,90,151],"agents":[22,63,91,152],"learn":[23],"short-range,":[24],"point-to-point":[25],"policies":[27,100],"capture":[29],"robot":[30,49,69,121],"dynamics":[31],"and":[32,96,104,113,131,156,178],"constraints":[34,192],"without":[35,188],"knowledge":[36],"of":[37,73],"the":[38,42,57,68,71,74,81,86,161,179,190],"large-scale":[39],"topology.":[40],"Next,":[41],"planners":[44],"provide":[45],"roadmaps":[46],"which":[47],"connect":[48],"configurations":[50],"can":[52],"be":[53],"successfully":[54,166],"navigated":[55],"by":[56],"agent.":[59],"same":[61],"are":[64,92],"used":[65,201],"to":[66,169],"control":[67],"under":[70,174],"direction":[72],"planning,":[75],"enabling":[76],"navigation.":[78],"use":[80],"Probabilistic":[82],"Roadmaps":[83],"(PRMs)":[84],"planner.":[88],"constructed":[93],"using":[94],"feature-based":[95],"deep":[97],"neural":[98],"net":[99],"in":[101,111,128,135,146,193,202],"continuous":[102],"state":[103],"action":[105],"spaces.":[106],"evaluate":[108],"both":[110,150],"simulation":[112],"on-robot,":[114],"on":[115,153],"two":[116],"tasks":[118],"non-trivial":[120],"dynamics:":[122],"end-to-end":[123],"differential":[124],"drive":[125],"indoor":[126,162],"office":[129],"environments,":[130],"aerial":[132,180],"cargo":[133,181],"delivery":[134,182],"urban":[136],"environments":[137],"load":[139],"displacement":[140],"constraints.":[141],"Our":[142],"results":[143],"show":[144],"improvement":[145],"over":[149,185],"their":[154],"own":[155],"traditional":[157],"planners.":[159],"In":[160],"task,":[164],"PRM-RL":[165],"completes":[167,183],"up":[168],"215":[170],"m":[171,187],"long":[172],"trajectories":[173],"noisy":[175],"sensor":[176],"conditions,":[177],"flights":[184],"1000":[186],"violating":[189],"an":[194],"environment":[195],"63":[196],"million":[197],"times":[198],"larger":[199],"than":[200],"training.":[203]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}