{"id":"https://openalex.org/W2987254226","doi":"https://doi.org/10.1109/iros40897.2019.8967945","title":"Comparison of Deep Reinforcement Learning Policies to Formal Methods for Moving Obstacle Avoidance","display_name":"Comparison of Deep Reinforcement Learning Policies to Formal Methods for Moving Obstacle Avoidance","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2987254226","doi":"https://doi.org/10.1109/iros40897.2019.8967945","mag":"2987254226"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8967945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967945","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":"conference-paper","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/A5101435111","display_name":"Arpit Garg","orcid":"https://orcid.org/0000-0001-5886-5822"},"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":"Arpit Garg","raw_affiliation_strings":["University of New Mexico, MSC01 11301 University of New Mexico,Department of Computer Science,Albuquerque,NM,USA,87131","Department of Computer Science, University of New Mexico, MSC01 11301 University of New Mexico, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Mexico, MSC01 11301 University of New Mexico,Department of Computer Science,Albuquerque,NM,USA,87131","institution_ids":["https://openalex.org/I169521973"]},{"raw_affiliation_string":"Department of Computer Science, University of New Mexico, MSC01 11301 University of New Mexico, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068480093","display_name":"Hao-Tien Lewis Chiang","orcid":"https://orcid.org/0000-0001-5418-6371"},"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":"Hao-Tien Lewis Chiang","raw_affiliation_strings":["University of New Mexico, MSC01 11301 University of New Mexico,Department of Computer Science,Albuquerque,NM,USA,87131","Department of Computer Science, University of New Mexico, MSC01 11301 University of New Mexico, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Mexico, MSC01 11301 University of New Mexico,Department of Computer Science,Albuquerque,NM,USA,87131","institution_ids":["https://openalex.org/I169521973"]},{"raw_affiliation_string":"Department of Computer Science, University of New Mexico, MSC01 11301 University of New Mexico, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021273969","display_name":"Satomi Sugaya","orcid":"https://orcid.org/0000-0003-3722-6591"},"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":"Satomi Sugaya","raw_affiliation_strings":["University of New Mexico, MSC01 11301 University of New Mexico,Department of Computer Science,Albuquerque,NM,USA,87131","Department of Computer Science, University of New Mexico, MSC01 11301 University of New Mexico, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Mexico, MSC01 11301 University of New Mexico,Department of Computer Science,Albuquerque,NM,USA,87131","institution_ids":["https://openalex.org/I169521973"]},{"raw_affiliation_string":"Department of Computer Science, University of New Mexico, MSC01 11301 University of New Mexico, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"middle","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":false,"raw_author_name":"Aleksandra Faust","raw_affiliation_strings":["Google AI,Mountain View,CA,USA,94043","Google AI, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google AI,Mountain View,CA,USA,94043","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google AI, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","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":["University of New Mexico, MSC01 11301 University of New Mexico,Department of Computer Science,Albuquerque,NM,USA,87131","Department of Computer Science, University of New Mexico, MSC01 11301 University of New Mexico, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Mexico, MSC01 11301 University of New Mexico,Department of Computer Science,Albuquerque,NM,USA,87131","institution_ids":["https://openalex.org/I169521973"]},{"raw_affiliation_string":"Department of Computer Science, University of New Mexico, MSC01 11301 University of New Mexico, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I169521973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2999,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.90191419,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3534","last_page":"3541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9979000091552734,"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":0.9973000288009644,"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":0.8851929903030396},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.833873450756073},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.7693346738815308},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6909862756729126},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.6663827300071716},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6444700956344604},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5334304571151733},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.525265634059906},{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.5158142447471619},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4708157181739807},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4326494634151459},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4101470708847046},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.37128758430480957},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3600793480873108},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1958860456943512},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1688779592514038},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.1337180733680725},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07930943369865417}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8851929903030396},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.833873450756073},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.7693346738815308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6909862756729126},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.6663827300071716},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6444700956344604},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5334304571151733},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.525265634059906},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.5158142447471619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4708157181739807},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4326494634151459},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4101470708847046},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.37128758430480957},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3600793480873108},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1958860456943512},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1688779592514038},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.1337180733680725},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07930943369865417},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros40897.2019.8967945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967945","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W980388479","https://openalex.org/W1576452626","https://openalex.org/W1825869920","https://openalex.org/W1984505032","https://openalex.org/W1995408953","https://openalex.org/W2002440441","https://openalex.org/W2007032806","https://openalex.org/W2009303086","https://openalex.org/W2066423936","https://openalex.org/W2067754486","https://openalex.org/W2080813827","https://openalex.org/W2108188253","https://openalex.org/W2116364955","https://openalex.org/W2121806728","https://openalex.org/W2145339207","https://openalex.org/W2165150801","https://openalex.org/W2170220350","https://openalex.org/W2267107524","https://openalex.org/W2406067508","https://openalex.org/W2411929833","https://openalex.org/W2624934338","https://openalex.org/W2736601468","https://openalex.org/W2745868649","https://openalex.org/W2806985155","https://openalex.org/W2810785043","https://openalex.org/W2890326782","https://openalex.org/W2912063360","https://openalex.org/W2949996623","https://openalex.org/W2962907394","https://openalex.org/W2963184939","https://openalex.org/W2964043796","https://openalex.org/W2964319688","https://openalex.org/W2991583441","https://openalex.org/W3100789280","https://openalex.org/W4205326910","https://openalex.org/W4302570325","https://openalex.org/W6684205842","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6750766805","https://openalex.org/W6752164047","https://openalex.org/W6753243525","https://openalex.org/W6754787993","https://openalex.org/W6770999945"],"related_works":["https://openalex.org/W2147391265","https://openalex.org/W2930076404","https://openalex.org/W2071957557","https://openalex.org/W2596413128","https://openalex.org/W1561646347","https://openalex.org/W2356867392","https://openalex.org/W2075718555","https://openalex.org/W2913749762","https://openalex.org/W2782776446","https://openalex.org/W2155948905"],"abstract_inverted_index":{"Deep":[0,14],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"has":[4],"recently":[5],"emerged":[6],"as":[7],"a":[8,58,65,94],"solution":[9,85],"for":[10,31,86],"moving":[11,90],"obstacle":[12,20,67,91],"avoidance.":[13],"RL":[15,39,100,139],"learns":[16],"to":[17,96,116,170,175],"simultaneously":[18],"predict":[19],"motions":[21],"and":[22,75,111,118],"corresponding":[23,174],"avoidance":[24,51,73,150],"actions":[25,112],"directly":[26],"from":[27,142],"robot":[28],"sensors,":[29],"even":[30],"obstacles":[32],"with":[33],"different":[34],"dynamics":[35,68],"models.":[36],"However,":[37],"deep":[38,99],"methods":[40],"typically":[41],"cannot":[42,47],"guarantee":[43],"policy":[44,74],"convergences,":[45],"i.e.,":[46],"provide":[48],"probabilistic":[49],"collision":[50,129,149],"guarantees.":[52,79],"In":[53,102],"contrast,":[54],"stochastic":[55],"reachability":[56],"(SR),":[57],"computationally":[59],"expensive":[60],"formal":[61],"method":[62],"that":[63,157],"employs":[64],"known":[66],"model,":[69],"identifies":[70],"the":[71,83,89,107,120,127,134,143,158,166,172,176],"optimal":[72,84,128,144],"provides":[76,93],"strict":[77],"convergence":[78],"The":[80,123],"availability":[81],"of":[82,88,113],"versions":[87],"problem":[92],"baseline":[95],"compare":[97,106],"trained":[98],"policies.":[101],"this":[103],"paper,":[104],"we":[105],"expected":[108],"cumulative":[109],"reward":[110],"these":[114],"policies":[115,140],"SR,":[117],"find":[119],"following.":[121],"1)":[122],"state-value":[124],"function":[125],"approximates":[126],"probability":[130],"well,":[131],"thus":[132,146],"explaining":[133],"high":[135],"empirical":[136],"performance.":[137],"2)":[138],"deviate":[141],"significantly":[145],"negatively":[147],"impacting":[148],"in":[151],"some":[152],"cases.":[153],"3)":[154],"Evidence":[155],"suggests":[156],"deviation":[159],"is":[160],"caused,":[161],"at":[162],"least":[163],"partially,":[164],"by":[165],"actor":[167],"net":[168],"failing":[169],"approximate":[171],"action":[173],"highest":[177],"state-action":[178],"value.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}