{"id":"https://openalex.org/W4387882771","doi":"https://doi.org/10.1109/mlsp55844.2023.10285997","title":"Deep Reinforcement Learning With Action Masking for Differential-Drive Robot Navigation Using Low-Cost Sensors","display_name":"Deep Reinforcement Learning With Action Masking for Differential-Drive Robot Navigation Using Low-Cost Sensors","publication_year":2023,"publication_date":"2023-09-17","ids":{"openalex":"https://openalex.org/W4387882771","doi":"https://doi.org/10.1109/mlsp55844.2023.10285997"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp55844.2023.10285997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp55844.2023.10285997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5081112273","display_name":"Konstantinos Tsampazis","orcid":null},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Konstantinos Tsampazis","raw_affiliation_strings":["Aristotle University of Thessaloniki,Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab,Department of Informatics,Thessaloniki,Greece","Department of Informatics, Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Aristotle University of Thessaloniki,Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab,Department of Informatics,Thessaloniki,Greece","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"Department of Informatics, Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039953793","display_name":"Manos Kirtas","orcid":"https://orcid.org/0000-0002-8670-0248"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Manos Kirtas","raw_affiliation_strings":["Aristotle University of Thessaloniki,Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab,Department of Informatics,Thessaloniki,Greece","Department of Informatics, Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Aristotle University of Thessaloniki,Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab,Department of Informatics,Thessaloniki,Greece","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"Department of Informatics, Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078968973","display_name":"Pavlos Tosidis","orcid":null},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Pavlos Tosidis","raw_affiliation_strings":["Aristotle University of Thessaloniki,Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab,Department of Informatics,Thessaloniki,Greece","Department of Informatics, Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Aristotle University of Thessaloniki,Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab,Department of Informatics,Thessaloniki,Greece","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"Department of Informatics, Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061050264","display_name":"Nikolaos Passalis","orcid":"https://orcid.org/0000-0003-1177-9139"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikolaos Passalis","raw_affiliation_strings":["Aristotle University of Thessaloniki,Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab,Department of Informatics,Thessaloniki,Greece","Department of Informatics, Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Aristotle University of Thessaloniki,Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab,Department of Informatics,Thessaloniki,Greece","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"Department of Informatics, Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041054091","display_name":"Anastasios Tefas","orcid":"https://orcid.org/0000-0003-1288-3667"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Anastasios Tefas","raw_affiliation_strings":["Aristotle University of Thessaloniki,Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab,Department of Informatics,Thessaloniki,Greece","Department of Informatics, Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Aristotle University of Thessaloniki,Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab,Department of Informatics,Thessaloniki,Greece","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"Department of Informatics, Computational Intelligence and Deep Learning (CIDL) Group, AIIA Lab, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081112273"],"corresponding_institution_ids":["https://openalex.org/I21370196"],"apc_list":null,"apc_paid":null,"fwci":0.3497,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66214673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9947999715805054,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.987500011920929,"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":0.8046342134475708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7577487230300903},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7373753786087036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6084556579589844},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5186542868614197},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.515454113483429},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.5058424472808838},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5013983249664307},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4882512390613556},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4253499507904053},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14562222361564636}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8046342134475708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577487230300903},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7373753786087036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6084556579589844},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5186542868614197},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.515454113483429},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.5058424472808838},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5013983249664307},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4882512390613556},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4253499507904053},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14562222361564636},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp55844.2023.10285997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp55844.2023.10285997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2014824949","https://openalex.org/W2155968351","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2963864421","https://openalex.org/W2996037775","https://openalex.org/W3012544020","https://openalex.org/W3031287835","https://openalex.org/W3037164854","https://openalex.org/W4298857966","https://openalex.org/W4310621382","https://openalex.org/W4312303251","https://openalex.org/W4320494745","https://openalex.org/W4366588842","https://openalex.org/W4393027313","https://openalex.org/W6637967152","https://openalex.org/W6684921986","https://openalex.org/W6741002519","https://openalex.org/W6772005887","https://openalex.org/W6775683342"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Driving":[0],"a":[1,6,10,23,48,65,69,79,123,144],"wheeled":[2,51],"differential-drive":[3,50],"robot":[4,52,76],"to":[5,15,74,78,86,122,150,156],"target":[7,80,125],"can":[8,35,100,119],"be":[9,36],"complicated":[11],"matter":[12],"when":[13,134],"trying":[14],"also":[16],"avoid":[17],"obstacles.":[18,83],"Usually,":[19],"such":[20,27],"robots":[21],"employ":[22],"variety":[24],"of":[25,90,108,137],"sensors,":[26],"as":[28],"LiDAR,":[29],"depth":[30],"cameras,":[31],"and":[32,60,106,154],"others,":[33],"that":[34,53,99],"quite":[37],"expensive.":[38],"To":[39],"this":[40,43],"end,":[41],"in":[42,127],"paper,":[44],"we":[45,94,113,142],"focus":[46],"on":[47,170],"simple":[49],"uses":[54],"only":[55],"inexpensive":[56],"ultrasonic":[57],"distance":[58],"sensors":[59],"touch":[61],"sensors.":[62],"We":[63],"propose":[64],"method":[66],"for":[67,164],"training":[68],"Reinforcement":[70],"Learning":[71],"(RL)":[72],"agent":[73,118],"perform":[75],"navigation":[77],"while":[81],"avoiding":[82],"In":[84],"order":[85],"increase":[87,102],"the":[88,91,103,109,116],"efficiency":[89],"proposed":[92,117],"approach":[93],"design":[95],"appropriate":[96],"action":[97],"masks":[98],"significantly":[101],"learning":[104],"speed":[105],"effectiveness":[107],"learned":[110],"policy.":[111],"As":[112],"experimentally":[114],"demonstrated,":[115],"robustly":[120],"navigate":[121],"given":[124],"even":[126,133],"unknown":[128,159],"procedurally":[129],"generated":[130],"environments,":[131],"or":[132],"denying":[135],"part":[136],"its":[138],"sensor":[139],"input.":[140],"Finally,":[141],"show":[143],"practical":[145],"use-case":[146],"using":[147],"object":[148],"detection":[149],"dynamically":[151],"search":[152],"for,":[153],"move":[155],"objects":[157],"within":[158],"environments.":[160],"The":[161],"code":[162],"used":[163],"conducted":[165],"experiments":[166],"is":[167],"available":[168],"online":[169],"Github.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}