{"id":"https://openalex.org/W3089737863","doi":"https://doi.org/10.1109/icra40945.2020.9197297","title":"Deep Imitative Reinforcement Learning for Temporal Logic Robot Motion Planning with Noisy Semantic Observations","display_name":"Deep Imitative Reinforcement Learning for Temporal Logic Robot Motion Planning with Noisy Semantic Observations","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3089737863","doi":"https://doi.org/10.1109/icra40945.2020.9197297","mag":"3089737863"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","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/A5076201548","display_name":"Qitong Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qitong Gao","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086742584","display_name":"Miroslav Paji\u0107","orcid":"https://orcid.org/0000-0002-5357-0117"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miroslav Pajic","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080808780","display_name":"Michael M. Zavlanos","orcid":"https://orcid.org/0000-0003-1748-8228"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael M. Zavlanos","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076201548"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":0.1954,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5003697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"518","issue":null,"first_page":"8490","last_page":"8496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9991000294685364,"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":0.9991000294685364,"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/T10142","display_name":"Formal Methods in Verification","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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":0.7734707593917847},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7357909083366394},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7068222761154175},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.696753203868866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6836596131324768},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5813467502593994},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5395632386207581},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4967963993549347},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4909417927265167},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.48967912793159485},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.48082172870635986},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47880277037620544},{"id":"https://openalex.org/keywords/linear-temporal-logic","display_name":"Linear temporal logic","score":0.46621400117874146},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4522148668766022},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.43719688057899475},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.19885608553886414},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1052379310131073}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7734707593917847},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7357909083366394},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7068222761154175},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.696753203868866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6836596131324768},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5813467502593994},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5395632386207581},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4967963993549347},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4909417927265167},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.48967912793159485},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48082172870635986},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47880277037620544},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.46621400117874146},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4522148668766022},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.43719688057899475},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.19885608553886414},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1052379310131073},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra40945.2020.9197297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W86372928","https://openalex.org/W1482467703","https://openalex.org/W1498432697","https://openalex.org/W1595409123","https://openalex.org/W1856263670","https://openalex.org/W1931877416","https://openalex.org/W1943821960","https://openalex.org/W1971086298","https://openalex.org/W1996295354","https://openalex.org/W2024802078","https://openalex.org/W2042587503","https://openalex.org/W2059470663","https://openalex.org/W2077578897","https://openalex.org/W2078151802","https://openalex.org/W2087939536","https://openalex.org/W2103728338","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2164429173","https://openalex.org/W2167805536","https://openalex.org/W2336416123","https://openalex.org/W2510352861","https://openalex.org/W2524638160","https://openalex.org/W2594675090","https://openalex.org/W2604855040","https://openalex.org/W2607319504","https://openalex.org/W2620827312","https://openalex.org/W2624912704","https://openalex.org/W2741248519","https://openalex.org/W2782656435","https://openalex.org/W2785998395","https://openalex.org/W2788862220","https://openalex.org/W2798923485","https://openalex.org/W2899702797","https://openalex.org/W2931553127","https://openalex.org/W2962957031","https://openalex.org/W2963117388","https://openalex.org/W2963376229","https://openalex.org/W2963604565","https://openalex.org/W2963778636","https://openalex.org/W2966183138","https://openalex.org/W2971204130","https://openalex.org/W3011120880","https://openalex.org/W3021964239","https://openalex.org/W3090827750","https://openalex.org/W4214717370","https://openalex.org/W4289541918","https://openalex.org/W4294584875","https://openalex.org/W6603443253","https://openalex.org/W6639061516","https://openalex.org/W6640174482","https://openalex.org/W6735926243","https://openalex.org/W6739554287","https://openalex.org/W6747682777","https://openalex.org/W6748089505","https://openalex.org/W6754842509","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W2124110813","https://openalex.org/W3168977894"],"abstract_inverted_index":{"In":[0],"this":[1,92],"paper,":[2],"we":[3],"propose":[4],"a":[5,48,60],"Deep":[6],"Imitative":[7],"Q-learning":[8,82,118],"(DIQL)":[9],"method":[10],"to":[11,20,79,84,112,116],"synthesize":[12],"control":[13],"policies":[14],"for":[15],"mobile":[16],"robots":[17],"that":[18,97],"need":[19],"satisfy":[21],"Linear":[22],"Temporal":[23],"Logic":[24],"(LTL)":[25],"specifications":[26],"using":[27,40,59,103],"noisy":[28],"semantic":[29,101],"observations":[30,102],"of":[31,47,89],"their":[32],"surroundings.":[33],"The":[34],"robot":[35,55],"sensing":[36],"error":[37],"is":[38,57,93],"modeled":[39,58],"probabilistic":[41,104],"labels":[42],"defined":[43],"over":[44],"the":[45,54,81,87,94,117],"states":[46],"Labeled":[49,61],"Transition":[50],"System":[51],"(LTS)":[52],"and":[53,107],"mobility":[56],"Markov":[62],"Decision":[63],"Process":[64],"(LMDP)":[65],"with":[66],"unknown":[67],"transition":[68],"probabilities.":[69],"We":[70],"use":[71],"existing":[72,109],"product-based":[73],"model":[74,110],"checkers":[75,111],"(PMCs)":[76],"as":[77],"experts":[78],"guide":[80],"algorithm":[83],"convergence.":[85],"To":[86],"best":[88],"our":[90],"knowledge,":[91],"first":[95],"approach":[96],"models":[98],"noise":[99],"in":[100],"labeling":[105],"functions":[106],"employs":[108],"provide":[113],"suboptimal":[114],"instructions":[115],"agent.":[119]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}