{"id":"https://openalex.org/W3023661178","doi":"https://doi.org/10.5220/0009821603140323","title":"Sim-to-Real Transfer with Incremental Environment Complexity for Reinforcement Learning of Depth-based Robot Navigation","display_name":"Sim-to-Real Transfer with Incremental Environment Complexity for Reinforcement Learning of Depth-based Robot Navigation","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3023661178","doi":"https://doi.org/10.5220/0009821603140323","mag":"3023661178"},"language":"en","primary_location":{"id":"doi:10.5220/0009821603140323","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0009821603140323","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0009821603140323","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058535422","display_name":"Thomas Chaffre","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I161929037","display_name":"Universit\u00e9 de Bretagne Occidentale","ror":"https://ror.org/01b8h3982","country_code":"FR","type":"education","lineage":["https://openalex.org/I161929037"]},{"id":"https://openalex.org/I169541294","display_name":"Flinders University","ror":"https://ror.org/01kpzv902","country_code":"AU","type":"education","lineage":["https://openalex.org/I169541294"]},{"id":"https://openalex.org/I4210123702","display_name":"Laboratoire des Sciences et Techniques de l\u2019Information de la Communication et de la Connaissance","ror":"https://ror.org/0266kfd37","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I180375564","https://openalex.org/I201181511","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I4210123702","https://openalex.org/I4210127572","https://openalex.org/I4210145102","https://openalex.org/I4210148559","https://openalex.org/I4210159245","https://openalex.org/I4405260085"]},{"id":"https://openalex.org/I4210148559","display_name":"\u00c9cole nationale sup\u00e9rieure de techniques avanc\u00e9es Bretagne","ror":"https://ror.org/059n54003","country_code":"FR","type":"education","lineage":["https://openalex.org/I201181511","https://openalex.org/I4210145102","https://openalex.org/I4210148559"]}],"countries":["AU","FR"],"is_corresponding":true,"raw_author_name":"Thomas Chaffre","raw_affiliation_strings":["Lab-STICC UMR CNRS 6285, ENSTA Bretagne, Brest, France, School of Computer Science, Engineering and Mathematics, Flinders University, Adelaide, SA, Australia, --- Select a Country ---","Lab-STICC_ENSTAB_CID_PRASYS","Flinders University [Adelaide, Australia]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lab-STICC UMR CNRS 6285, ENSTA Bretagne, Brest, France, School of Computer Science, Engineering and Mathematics, Flinders University, Adelaide, SA, Australia, --- Select a Country ---","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I161929037","https://openalex.org/I169541294","https://openalex.org/I4210148559","https://openalex.org/I4210123702"]},{"raw_affiliation_string":"Lab-STICC_ENSTAB_CID_PRASYS","institution_ids":[]},{"raw_affiliation_string":"Flinders University [Adelaide, Australia]","institution_ids":["https://openalex.org/I169541294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055919342","display_name":"Julien Moras","orcid":"https://orcid.org/0000-0003-2959-7544"},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I2801658355","display_name":"Office National d'\u00c9tudes et de Recherches A\u00e9rospatiales","ror":"https://ror.org/005y2ap84","country_code":"FR","type":"facility","lineage":["https://openalex.org/I2801658355"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Julien Moras","raw_affiliation_strings":["DTIS, ONERA - The French Aerospace Lab, Universit\u00e9 Paris Saclay, F-91123 Palaiseau, France, --- Select a Country ---","DTIS, ONERA, Universit\u00e9 Paris Saclay [Palaiseau]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DTIS, ONERA - The French Aerospace Lab, Universit\u00e9 Paris Saclay, F-91123 Palaiseau, France, --- Select a Country ---","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I2801658355"]},{"raw_affiliation_string":"DTIS, ONERA, Universit\u00e9 Paris Saclay [Palaiseau]","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I2801658355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018897861","display_name":"Adrien Chan-Hon-Tong","orcid":"https://orcid.org/0000-0002-7333-2765"},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I2801658355","display_name":"Office National d'\u00c9tudes et de Recherches A\u00e9rospatiales","ror":"https://ror.org/005y2ap84","country_code":"FR","type":"facility","lineage":["https://openalex.org/I2801658355"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Adrien Chan-Hon-Tong","raw_affiliation_strings":["DTIS, ONERA - The French Aerospace Lab, Universit\u00e9 Paris Saclay, F-91123 Palaiseau, France, --- Select a Country ---","DTIS, ONERA, Universit\u00e9 Paris Saclay [Palaiseau]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DTIS, ONERA - The French Aerospace Lab, Universit\u00e9 Paris Saclay, F-91123 Palaiseau, France, --- Select a Country ---","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I2801658355"]},{"raw_affiliation_string":"DTIS, ONERA, Universit\u00e9 Paris Saclay [Palaiseau]","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I2801658355"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072536302","display_name":"Julien Marzat","orcid":"https://orcid.org/0000-0002-5041-272X"},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I2801658355","display_name":"Office National d'\u00c9tudes et de Recherches A\u00e9rospatiales","ror":"https://ror.org/005y2ap84","country_code":"FR","type":"facility","lineage":["https://openalex.org/I2801658355"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Julien Marzat","raw_affiliation_strings":["DTIS, ONERA - The French Aerospace Lab, Universit\u00e9 Paris Saclay, F-91123 Palaiseau, France, --- Select a Country ---","DTIS, ONERA, Universit\u00e9 Paris Saclay [Palaiseau]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DTIS, ONERA - The French Aerospace Lab, Universit\u00e9 Paris Saclay, F-91123 Palaiseau, France, --- Select a Country ---","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I2801658355"]},{"raw_affiliation_string":"DTIS, ONERA, Universit\u00e9 Paris Saclay [Palaiseau]","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I2801658355"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5058535422"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I161929037","https://openalex.org/I169541294","https://openalex.org/I4210123702","https://openalex.org/I4210148559"],"apc_list":null,"apc_paid":null,"fwci":0.5436,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72983234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"314","last_page":"323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9970999956130981,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9898999929428101,"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":0.8121293783187866},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6759752035140991},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6005308628082275},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.582000195980072},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.47667956352233887},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.45879197120666504},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.44641056656837463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43912553787231445},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4099237322807312},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.04719221591949463}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8121293783187866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6759752035140991},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6005308628082275},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.582000195980072},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.47667956352233887},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.45879197120666504},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.44641056656837463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43912553787231445},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4099237322807312},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.04719221591949463}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.5220/0009821603140323","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0009821603140323","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.14684","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.14684","pdf_url":"https://arxiv.org/pdf/2004.14684","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"pmh:oai:HAL:hal-02958155v1","is_oa":false,"landing_page_url":"https://ensta.hal.science/hal-02958155","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"17th International Conference on Informatics, Automation and Robotics, ICINCO 2020, Jul 2020, Online, France. pp.314-323","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.2004.14684","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.14684","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.5220/0009821603140323","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0009821603140323","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1130790960","https://openalex.org/W1581407678","https://openalex.org/W1757796397","https://openalex.org/W1996615911","https://openalex.org/W2110762409","https://openalex.org/W2151834591","https://openalex.org/W2155027007","https://openalex.org/W2167340365","https://openalex.org/W2173248099","https://openalex.org/W2218842719","https://openalex.org/W2296073425","https://openalex.org/W2362143032","https://openalex.org/W2513734981","https://openalex.org/W2534269850","https://openalex.org/W2596367596","https://openalex.org/W2605102758","https://openalex.org/W2618092744","https://openalex.org/W2732319713","https://openalex.org/W2739161005","https://openalex.org/W2746411854","https://openalex.org/W2766447205","https://openalex.org/W2781726626","https://openalex.org/W2912063360","https://openalex.org/W2918642789","https://openalex.org/W2925306934","https://openalex.org/W2940868402","https://openalex.org/W2942608247","https://openalex.org/W2962747693","https://openalex.org/W2962957005","https://openalex.org/W2963428623","https://openalex.org/W2963630234","https://openalex.org/W2963871073","https://openalex.org/W2964121744","https://openalex.org/W2970971581","https://openalex.org/W2980825073","https://openalex.org/W2981030070","https://openalex.org/W3102327032","https://openalex.org/W3104933725","https://openalex.org/W3124420883"],"related_works":["https://openalex.org/W2805209921","https://openalex.org/W2907103250","https://openalex.org/W1534851618","https://openalex.org/W3041867744","https://openalex.org/W4282981148","https://openalex.org/W2115138863","https://openalex.org/W2124695578","https://openalex.org/W1485735559","https://openalex.org/W3214999573","https://openalex.org/W2164114810"],"abstract_inverted_index":{"Transferring":[0],"learning-based":[1],"models":[2,38],"to":[3,18,95,115,161],"the":[4,10,19,29,60,66,73,81,118,124,164,167],"real":[5,26,77,84,125,157],"world":[6,68],"remains":[7],"one":[8],"of":[9,21,33,51,166],"hardest":[11],"problems":[12],"in":[13,42,76,123,143,154],"model-free":[14],"control":[15],"theory.":[16],"Due":[17],"cost":[20],"data":[22],"collection":[23],"on":[24,80],"a":[25,43,87,97,103,135,140,144,172,178],"robot":[27,137],"and":[28,57,65,156],"limited":[30],"sample":[31],"efficiency":[32,165],"Deep":[34],"Reinforcement":[35],"Learning":[36],"algorithms,":[37],"are":[39,159],"usually":[40],"trained":[41],"simulator":[44],"which":[45,170],"theoretically":[46],"provides":[47],"an":[48],"infinite":[49],"amount":[50],"data.":[52],"Despite":[53],"offering":[54],"unbounded":[55],"trial":[56],"error":[58],"runs,":[59],"reality":[61],"gap":[62],"between":[63],"simulation":[64],"physical":[67],"brings":[69],"little":[70],"guarantee":[71],"about":[72],"policy":[74],"behavior":[75],"operation.":[78],"Depending":[79],"problem,":[82],"expensive":[83],"fine-tuning":[85],"and/or":[86],"complex":[88],"domain":[89],"randomization":[90],"strategy":[91,108],"may":[92],"be":[93],"required":[94],"produce":[96],"relevant":[98],"policy.":[99],"In":[100],"this":[101],"paper,":[102],"Soft-Actor":[104],"Critic":[105],"(SAC)":[106],"training":[107,122],"using":[109],"incremental":[110],"environment":[111,146],"complexity":[112],"is":[113,130],"proposed":[114,168],"drastically":[116],"reduce":[117],"need":[119],"for":[120],"additional":[121],"world.":[126],"The":[127],"application":[128],"addressed":[129],"depth-based":[131],"mapless":[132],"navigation,":[133],"where":[134],"mobile":[136],"should":[138],"reach":[139],"given":[141],"waypoint":[142],"cluttered":[145],"with":[147],"no":[148],"prior":[149],"mapping":[150],"information.":[151],"Experimental":[152],"results":[153],"simulated":[155],"environments":[158],"presented":[160],"assess":[162],"quantitatively":[163],"approach,":[169],"demonstrated":[171],"success":[173],"rate":[174],"twice":[175],"higher":[176],"than":[177],"naive":[179],"strategy.":[180]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2020-05-13T00:00:00"}