{"id":"https://openalex.org/W3210166519","doi":null,"title":"Deep Reinforcement learning approach towards autonomous navigation and its challenges","display_name":"Deep Reinforcement learning approach towards autonomous navigation and its challenges","alternate_titles":[],"publication_year":2021,"publication_date":"2021-10-27","ids":{"openalex":"https://openalex.org/W3210166519","mag":"3210166519"},"language":"en","primary_location":{"id":"mag:3210166519","doi":null,"is_oa":false,"landing_page_url":"http://thedesignengineering.com/index.php/DE/article/view/5788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Design Engineering","raw_type":null},"parent_works":[],"lineage":["https://openalex.org/W3210166519"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"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/A5111514418","display_name":"G. Suganya","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"contributor_roles":[],"raw_author_name":"G. Suganya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5111514418"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"reviewed_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7474","last_page":"7487"},"is_retracted":false,"is_pulled":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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.0,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/autonomous-navigation","display_name":"autonomous navigation","score":0.9160000085830688},{"id":"https://openalex.org/keywords/visual-navigation","display_name":"visual navigation","score":0.753000020980835},{"id":"https://openalex.org/keywords/robot-navigation","display_name":"robot navigation","score":0.7120000123977661},{"id":"https://openalex.org/keywords/reward-learning","display_name":"reward learning","score":0.5839999914169312},{"id":"https://openalex.org/keywords/learning-agents","display_name":"learning agents","score":0.33799999952316284},{"id":"https://openalex.org/keywords/policy-optimization","display_name":"policy optimization","score":0.5189999938011169}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8856186866760254},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7110854387283325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6835492253303528},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.49753955006599426},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.49658137559890747},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.47327089309692383},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.44732779264450073},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.439073383808136},{"id":"https://openalex.org/C117270229","wikidata":"https://www.wikidata.org/wiki/Q5957539","display_name":"Hyper-heuristic","level":5,"score":0.43042251467704773},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3940108120441437},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3855205774307251},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.25680649280548096},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3210166519","doi":null,"is_oa":false,"landing_page_url":"http://thedesignengineering.com/index.php/DE/article/view/5788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Design Engineering","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387193993","https://openalex.org/W2987244635","https://openalex.org/W3044499041","https://openalex.org/W3011596115","https://openalex.org/W2896581723","https://openalex.org/W2980730703","https://openalex.org/W4396908728","https://openalex.org/W4408875235","https://openalex.org/W3161551690","https://openalex.org/W3198393112"],"abstract_inverted_index":{"Reinforcement":[0,89],"Learning":[1,8,90],"(RL)":[2],"is":[3,112],"a":[4,15,98,102],"subset":[5],"of":[6,17,81,85,109],"Machine":[7],"that":[9],"trains":[10],"an":[11],"agent":[12,32,111],"to":[13,34,59,104,130],"make":[14],"series":[16],"decisions":[18],"and":[19,93,126],"take":[20],"actions":[21,43],"by":[22,38,135],"interacting":[23],"directly":[24],"with":[25,53],"the":[26,31,36,39,68,79,106,110,118,121,127,132,136],"environment.":[27],"In":[28],"this":[29,96],"approach":[30],"learns":[33],"attain":[35],"goal":[37],"response":[40],"from":[41],"its":[42],"as":[44],"rewards":[45,133],"or":[46],"punishment.":[47],"Recent":[48],"advances":[49],"in":[50,67,78],"RL":[51],"combined":[52],"deep":[54],"learning":[55,107],"methods":[56],"have":[57],"led":[58],"breakthrough":[60],"research":[61],"\u00a0in":[62],"solving":[63],"many":[64],"complex":[65],"problems":[66],"field":[69],"of\u00a0":[70],"artificial":[71],"intelligence.":[72],"This":[73,114],"paper":[74,115],"presents":[75],"recent":[76],"literature":[77],"area":[80],"autonomous":[82],"visual":[83],"navigation":[84],"robots":[86],"using":[87],"Deep":[88],"(DRL)":[91],"algorithms":[92,119],"methods.":[94],"\u00a0In":[95],"paper,":[97],"proposal":[99],"for":[100,124],"developing":[101],"method":[103],"improve":[105],"capability":[108],"presented.":[113],"also":[116],"describes":[117],"evaluated,":[120],"environment":[122],"used":[123],"implementation":[125],"policy":[128],"applied":[129],"maximize":[131],"earned":[134],"agent.":[137]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3210166519","counts_by_year":[],"updated_date":"2025-11-06T04:12:42.849631","created_date":"2021-11-08T00:00:00"}
