{"id":"https://openalex.org/W3196776285","doi":"https://doi.org/10.1145/3461353.3461365","title":"Learning Navigation Policies for Mobile Robots in Deep Reinforcement Learning with Random Network Distillation","display_name":"Learning Navigation Policies for Mobile Robots in Deep Reinforcement Learning with Random Network Distillation","publication_year":2021,"publication_date":"2021-03-05","ids":{"openalex":"https://openalex.org/W3196776285","doi":"https://doi.org/10.1145/3461353.3461365","mag":"3196776285"},"language":"en","primary_location":{"id":"doi:10.1145/3461353.3461365","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461353.3461365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 the 5th International Conference on Innovation in Artificial Intelligence","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/A5022837068","display_name":"Lifan Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lifan Pan","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065183587","display_name":"Anyi Li","orcid":"https://orcid.org/0009-0008-1092-0157"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anyi Li","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101997874","display_name":"Jun Ma","orcid":"https://orcid.org/0000-0003-2258-0854"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Ma","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061104105","display_name":"Jianmin Ji","orcid":"https://orcid.org/0000-0002-1515-0402"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianmin Ji","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.879,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76917389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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/T12288","display_name":"Optimization and Search Problems","score":0.9937999844551086,"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":0.8885233402252197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.715681791305542},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.6881500482559204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.626470148563385},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6033403873443604},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5546068549156189},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5040063261985779},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4696345329284668},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.46439534425735474},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.46096158027648926},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.45324766635894775},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4366809129714966},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.4340885281562805},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.4186108112335205},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3659871816635132},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14851775765419006}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8885233402252197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715681791305542},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.6881500482559204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.626470148563385},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6033403873443604},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5546068549156189},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5040063261985779},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4696345329284668},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.46439534425735474},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.46096158027648926},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.45324766635894775},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4366809129714966},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.4340885281562805},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.4186108112335205},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3659871816635132},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14851775765419006},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3461353.3461365","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461353.3461365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 the 5th International Conference on Innovation in Artificial Intelligence","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":6,"referenced_works":["https://openalex.org/W779494576","https://openalex.org/W2101524054","https://openalex.org/W2963019567","https://openalex.org/W2963428623","https://openalex.org/W2969277962","https://openalex.org/W3081171811"],"related_works":["https://openalex.org/W4381746183","https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908"],"abstract_inverted_index":{"Learning":[0,22],"navigation":[1,69,109,233],"policies":[2],"considers":[3],"the":[4,32,37,47,55,80,112,119,124,128,136,142,147,161,174,193,220],"task":[5,38],"of":[6,127,241],"training":[7],"a":[8,44,50,76,86,101,178,224],"model":[9,222],"that":[10,116,180,190],"can":[11,206,228,244],"find":[12],"collision-free":[13,77],"paths":[14],"for":[15,36,46,53,66],"mobile":[16],"robots,":[17],"where":[18],"various":[19],"Deep":[20],"Reinforcement":[21],"(DRL)":[23],"methods":[24],"have":[25],"been":[26,183],"applied":[27],"with":[28,93,149,196,203],"promising":[29],"results.":[30],"However,":[31],"natural":[33],"reward":[34,52,138,145,151,163,194,198],"function":[35,195],"is":[39,72,164],"usually":[40],"sparse,":[41],"i.e.,":[42],"obtaining":[43],"penalty":[45],"collision":[48,230],"and":[49,91,123,211],"positive":[51],"arriving":[54],"target":[56],"position,":[57],"which":[58,83,172,227],"makes":[59],"it":[60,71],"difficult":[61],"to":[62,74,85,105,176,223],"learn.":[63],"In":[64,96,159],"particular,":[65],"some":[67],"complex":[68],"environments,":[70],"hard":[73],"search":[75],"path":[78],"by":[79,154,166,191,200],"random":[81,155],"exploration,":[82],"leads":[84],"rather":[87],"slow":[88],"learning":[89],"speed":[90],"solutions":[92,202],"poor":[94],"performance.":[95],"this":[97],"paper,":[98],"we":[99,140],"propose":[100],"DRL":[102],"based":[103],"approach":[104],"train":[106],"an":[107],"end-to-end":[108],"planner,":[110],"i.e,":[111],"policy":[113],"neural":[114],"network,":[115],"directly":[117],"translates":[118],"local":[120],"grid":[121],"map":[122],"relative":[125],"goal":[126],"robot":[129],"into":[130],"its":[131],"moving":[132],"actions.":[133],"To":[134],"handle":[135],"sparse":[137],"problem,":[139],"augment":[141],"normal":[143],"extrinsic":[144],"from":[146,170],"environment":[148],"intrinsic":[150,162,197],"signals":[152,199],"measured":[153],"network":[156],"distillation":[157],"(RND).":[158],"specific,":[160],"calculated":[165],"two":[167],"different":[168],"networks":[169],"RND,":[171,201],"encourages":[173],"agent":[175],"explore":[177],"state":[179],"has":[181],"not":[182],"seen":[184],"before.":[185],"The":[186],"experimental":[187],"results":[188],"show":[189],"augmenting":[192],"better":[204],"performance":[205],"be":[207,245],"learned":[208],"more":[209,212],"efficiently":[210],"stably":[213],"in":[214,232],"our":[215,242],"approach.":[216],"We":[217],"also":[218],"deploy":[219],"trained":[221],"real":[225],"robot,":[226],"perform":[229],"avoidance":[231],"tasks":[234],"without":[235],"any":[236],"parameter":[237],"tuning.":[238],"A":[239],"video":[240],"experiments":[243],"found":[246],"at":[247],"https://youtu.be/b1GJrWfO8pw.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}