{"id":"https://openalex.org/W4405709888","doi":"https://doi.org/10.1109/robot61475.2024.10796966","title":"D-TOP: Deep Reinforcement Learning with Tuneable Optimization for Autonomous Navigation","display_name":"D-TOP: Deep Reinforcement Learning with Tuneable Optimization for Autonomous Navigation","publication_year":2024,"publication_date":"2024-11-06","ids":{"openalex":"https://openalex.org/W4405709888","doi":"https://doi.org/10.1109/robot61475.2024.10796966"},"language":"en","primary_location":{"id":"doi:10.1109/robot61475.2024.10796966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot61475.2024.10796966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 7th Iberian Robotics Conference (ROBOT)","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/A5101541684","display_name":"Diego Mart\u00ednez","orcid":"https://orcid.org/0000-0002-2029-2851"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Diego Martinez-Baselga","raw_affiliation_strings":["University of Zaragoza,Aragon Institute of Engineering Research (I3A),Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zaragoza,Aragon Institute of Engineering Research (I3A),Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018256987","display_name":"Luis Riazuelo","orcid":"https://orcid.org/0000-0002-6722-5541"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luis Riazuelo","raw_affiliation_strings":["University of Zaragoza,Aragon Institute of Engineering Research (I3A),Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zaragoza,Aragon Institute of Engineering Research (I3A),Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113286835","display_name":"Luis Montano","orcid":"https://orcid.org/0000-0002-0449-2300"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luis Montano","raw_affiliation_strings":["University of Zaragoza,Aragon Institute of Engineering Research (I3A),Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zaragoza,Aragon Institute of Engineering Research (I3A),Spain","institution_ids":["https://openalex.org/I255234318"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I255234318"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9922000169754028,"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":0.9922000169754028,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9251999855041504,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9168999791145325,"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":0.8649629354476929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6704674959182739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5589506030082703},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.347922146320343}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8649629354476929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6704674959182739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5589506030082703},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.347922146320343}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robot61475.2024.10796966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot61475.2024.10796966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 7th Iberian Robotics Conference (ROBOT)","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/W192919555","https://openalex.org/W2133552987","https://openalex.org/W2150468603","https://openalex.org/W2163061173","https://openalex.org/W2765302304","https://openalex.org/W2810439382","https://openalex.org/W2890001928","https://openalex.org/W2964319688","https://openalex.org/W2968104655","https://openalex.org/W2969277962","https://openalex.org/W2970857152","https://openalex.org/W2982312374","https://openalex.org/W3021487874","https://openalex.org/W3131623996","https://openalex.org/W3203477356","https://openalex.org/W3206010851","https://openalex.org/W4200004515","https://openalex.org/W4226389608","https://openalex.org/W4383108601","https://openalex.org/W4383108695","https://openalex.org/W4386718967","https://openalex.org/W4389666876","https://openalex.org/W6683300800","https://openalex.org/W6733118196","https://openalex.org/W6751629939","https://openalex.org/W6767112054","https://openalex.org/W6776837600","https://openalex.org/W6794172776","https://openalex.org/W6846310611"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"The":[0,103],"field":[1],"of":[2,61,151,154,158,204,207],"autonomous":[3,62,135],"navigation":[4,92,136,190],"has":[5],"seen":[6],"significant":[7],"advancements":[8],"in":[9,21,46,84],"recent":[10],"years,":[11],"with":[12,91,100,113,171],"deep":[13],"reinforcement":[14],"learning":[15],"(DRL)":[16],"algorithms":[17,28],"demonstrating":[18],"impressive":[19],"capabilities":[20],"various":[22],"settings":[23],"over":[24],"traditional":[25],"methods.":[26],"DRL":[27,50,145],"plan":[29],"their":[30],"motion":[31],"according":[32],"to":[33,41,57,106,146,166,183,188,201],"what":[34],"they":[35],"have":[36,54],"experienced":[37],"during":[38],"training,":[39],"trying":[40],"optimize":[42],"the":[43,47,55,59,66,101,111,148,152,155,159,177,185,205,208,222],"task":[44],"encoded":[45,90],"reward.":[48],"However,":[49],"methods":[51],"do":[52,107],"not":[53],"ability":[56],"change":[58],"behavior":[60,187],"robots":[63],"based":[64],"on":[65,176,221],"environment;":[67],"which":[68,117],"is":[69,109],"crucial":[70],"to,":[71],"for":[72],"example,":[73],"ensure":[74],"safe":[75],"and":[76,125,143,210],"understandable":[77],"interactions":[78],"around":[79],"humans":[80],"or":[81,97],"efficient":[82],"trajectories":[83],"open":[85],"spaces.":[86],"These":[87],"behaviors":[88,219],"are":[89,95],"metrics":[93],"that":[94,138,174,195,212],"directly":[96],"indirectly":[98],"recorded":[99],"task.":[102],"only":[104],"way":[105],"so":[108],"retraining":[110],"agent":[112],"other":[114,202],"reward":[115,123,126],"function,":[116],"requires":[118],"long":[119],"computational":[120],"time,":[121],"complex":[122],"shaping":[124],"engineering.":[127],"In":[128],"this":[129],"article,":[130],"we":[131,162],"propose":[132,163],"a":[133,164],"novel":[134],"approach":[137],"uses":[139],"an":[140],"attention-based":[141],"network":[142],"distributional":[144],"estimate":[147],"probability":[149,178],"distribution":[150],"values":[153],"possible":[156],"velocities":[157],"robot.":[160],"Then,":[161],"framework":[165],"modify":[167],"its":[168],"action":[169],"selection":[170],"adjustable":[172],"parameters":[173],"depend":[175],"distribution.":[179],"This":[180],"process":[181],"enables":[182],"tailor":[184],"agent's":[186],"specific":[189],"metrics.":[191],"We":[192],"offer":[193],"experiments":[194],"validate":[196],"our":[197,213],"method,":[198],"comparing":[199],"it":[200],"planners":[203],"state":[206],"art":[209],"showing":[211],"method":[214],"can":[215],"find":[216],"different":[217],"optimal":[218],"depending":[220],"scenario":[223],"needs.":[224]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}