{"id":"https://openalex.org/W3150979816","doi":"https://doi.org/10.1109/ieeeconf49454.2021.9382661","title":"Autonomous Navigation in Complex Environments using Memory-Aided Deep Reinforcement Learning","display_name":"Autonomous Navigation in Complex Environments using Memory-Aided Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-01-11","ids":{"openalex":"https://openalex.org/W3150979816","doi":"https://doi.org/10.1109/ieeeconf49454.2021.9382661","mag":"3150979816"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf49454.2021.9382661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf49454.2021.9382661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/SICE International Symposium on System Integration (SII)","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/A5044968499","display_name":"Linh K\u00e4stner","orcid":"https://orcid.org/0000-0001-5263-4687"},"institutions":[{"id":"https://openalex.org/I4210148503","display_name":"Fraunhofer Institute for Production Systems and Design Technology","ror":"https://ror.org/045eg9c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210148503","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Linh Kastner","raw_affiliation_strings":["Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany","institution_ids":["https://openalex.org/I4210148503","https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033136997","display_name":"Zhengcheng Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148503","display_name":"Fraunhofer Institute for Production Systems and Design Technology","ror":"https://ror.org/045eg9c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210148503","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zhengcheng Shen","raw_affiliation_strings":["Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany","institution_ids":["https://openalex.org/I4210148503","https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013523657","display_name":"Cornelius Marx","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148503","display_name":"Fraunhofer Institute for Production Systems and Design Technology","ror":"https://ror.org/045eg9c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210148503","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornelius Marx","raw_affiliation_strings":["Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany","institution_ids":["https://openalex.org/I4210148503","https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002499102","display_name":"Jens Lambrecht","orcid":"https://orcid.org/0000-0002-1017-9548"},"institutions":[{"id":"https://openalex.org/I4210148503","display_name":"Fraunhofer Institute for Production Systems and Design Technology","ror":"https://ror.org/045eg9c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210148503","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens Lambrecht","raw_affiliation_strings":["Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany","institution_ids":["https://openalex.org/I4210148503","https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044968499"],"corresponding_institution_ids":["https://openalex.org/I4210148503","https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":0.0969,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.35702825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"170","last_page":"175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8476283550262451},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7380900382995605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5871152281761169},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5542358160018921},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5421626567840576},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5229071974754333},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4886208176612854},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.44331634044647217},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4121486246585846},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35691016912460327}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8476283550262451},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7380900382995605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5871152281761169},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5542358160018921},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5421626567840576},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5229071974754333},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4886208176612854},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.44331634044647217},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4121486246585846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35691016912460327}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf49454.2021.9382661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf49454.2021.9382661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/SICE International Symposium on System Integration (SII)","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":29,"referenced_works":["https://openalex.org/W1484387568","https://openalex.org/W1977655452","https://openalex.org/W2057134775","https://openalex.org/W2095487261","https://openalex.org/W2098774185","https://openalex.org/W2100677568","https://openalex.org/W2108734173","https://openalex.org/W2125612430","https://openalex.org/W2139053308","https://openalex.org/W2145339207","https://openalex.org/W2336416123","https://openalex.org/W2342840547","https://openalex.org/W2532493213","https://openalex.org/W2556215627","https://openalex.org/W2796447411","https://openalex.org/W2950471160","https://openalex.org/W2963946945","https://openalex.org/W2967453881","https://openalex.org/W2969608721","https://openalex.org/W2971384749","https://openalex.org/W3041202696","https://openalex.org/W3091957856","https://openalex.org/W3100838107","https://openalex.org/W6674884181","https://openalex.org/W6676172287","https://openalex.org/W6696324988","https://openalex.org/W6704559304","https://openalex.org/W6750106230","https://openalex.org/W6750185400"],"related_works":["https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W217960748","https://openalex.org/W3125814499","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W2122871747","https://openalex.org/W3114279067"],"abstract_inverted_index":{"Mobile":[0],"robots":[1],"have":[2,35],"gained":[3],"increased":[4],"importance":[5],"within":[6,120,165],"industrial":[7,30],"tasks":[8],"such":[9,84],"as":[10,85],"commissioning,":[11],"delivery":[12],"or":[13,89],"operation":[14],"in":[15,22,29,39,81],"hazardous":[16],"environments.":[17],"The":[18,136],"ability":[19],"to":[20,60,67,71,108,140,151,169],"navigate":[21,141],"unknown":[23,42],"and":[24,44,51,64,129,161],"complex":[25,82,159,166],"environments":[26,83,160,167],"is":[27,92,138],"paramount":[28],"robotics.":[31],"Reinforcement":[32],"learning":[33,117],"approaches":[34,56],"shown":[36],"remarkable":[37],"success":[38],"dealing":[40],"with":[41,110,132],"situations":[43],"react":[45],"accordingly":[46],"without":[47],"manually":[48],"engineered":[49],"guidelines":[50],"overconservative":[52],"measures.":[53],"However,":[54],"these":[55,111],"are":[57,65,148],"often":[58],"restricted":[59],"short":[61],"range":[62],"navigation":[63,80],"prone":[66],"local":[68],"minima":[69],"due":[70],"a":[72,75,102,115,121,133],"lack":[73],"of":[74,104,125],"memory":[76,134],"module.":[77,135],"Thus,":[78],"the":[79,155],"mazes,":[86],"long":[87],"corridors":[88],"concave":[90],"areas":[91],"still":[93],"an":[94],"open":[95],"frontier.":[96],"In":[97],"this":[98],"paper,":[99],"we":[100],"incorporate":[101],"variety":[103],"recurrent":[105],"neural":[106],"networks":[107],"cope":[109],"challenges.":[112],"We":[113,153],"train":[114],"reinforcement":[116],"based":[118],"agent":[119,137],"2D":[122],"simulation":[123],"environment":[124],"our":[126],"previous":[127],"work":[128],"extend":[130],"it":[131],"able":[139],"solely":[142],"on":[143,157],"sensor":[144],"data":[145],"observations":[146],"which":[147],"directly":[149],"mapped":[150],"actions.":[152],"evaluate":[154],"performance":[156],"different":[158],"achieve":[162],"enhanced":[163],"results":[164],"compared":[168],"memory-free":[170],"baseline":[171],"approaches.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-23T07:41:27.035349","created_date":"2025-10-10T00:00:00"}