{"id":"https://openalex.org/W4387031540","doi":"https://doi.org/10.48550/arxiv.2309.12807","title":"Teacher-Student Reinforcement Learning for Mapless Navigation using a Planetary Space Rover","display_name":"Teacher-Student Reinforcement Learning for Mapless Navigation using a Planetary Space Rover","publication_year":2023,"publication_date":"2023-09-22","ids":{"openalex":"https://openalex.org/W4387031540","doi":"https://doi.org/10.48550/arxiv.2309.12807"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.12807","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.12807","pdf_url":"https://arxiv.org/pdf/2309.12807","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.12807","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104173836","display_name":"Anton Bj\u00f8rndahl Mortensen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mortensen, Anton Bj\u00f8rndahl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046287089","display_name":"Emil Pedersen","orcid":"https://orcid.org/0000-0001-8996-6984","observed_orcids":["https://orcid.org/0000-0001-8996-6984"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pedersen, Emil Tribler","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092938859","display_name":"Laia Vives Benedicto","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benedicto, Laia Vives","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092938860","display_name":"Lionel Burg","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Burg, Lionel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104173837","display_name":"Mads Rossen Madsen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Madsen, Mads Rossen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5048839097","display_name":"Simon B\u00f8gh","orcid":"https://orcid.org/0000-0002-5960-4365","observed_orcids":["https://orcid.org/0000-0002-5960-4365"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"B\u00f8gh, Simon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.0,"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/T11978","display_name":"Soil Mechanics and Vehicle Dynamics","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mapless-navigation","display_name":"mapless navigation","score":0.9210000038146973},{"id":"https://openalex.org/keywords/planetary-rovers","display_name":"planetary rovers","score":0.7799999713897705},{"id":"https://openalex.org/keywords/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.9490000009536743},{"id":"https://openalex.org/keywords/reality-gap","display_name":"reality gap","score":0.8820000290870667}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.671261191368103},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.6502033472061157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5660883188247681},{"id":"https://openalex.org/C104060986","wikidata":"https://www.wikidata.org/wiki/Q180046","display_name":"Space exploration","level":2,"score":0.5338163375854492},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5320937037467957},{"id":"https://openalex.org/C65414064","wikidata":"https://www.wikidata.org/wiki/Q484105","display_name":"Autonomy","level":2,"score":0.47849029302597046},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4585748314857483},{"id":"https://openalex.org/C83260615","wikidata":"https://www.wikidata.org/wiki/Q6773121","display_name":"Mars Exploration Program","level":2,"score":0.4258491098880768},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4079738259315491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35261619091033936},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.33427825570106506},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2944294810295105},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.109508216381073},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10366412997245789},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.10008209943771362},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2309.12807","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.12807","pdf_url":"https://arxiv.org/pdf/2309.12807","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:publications/f6daa4c4-7769-441d-a61d-5d6dcab7c383","doi":null,"is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/f6daa4c4-7769-441d-a61d-5d6dcab7c383","pdf_url":"https://arxiv.org/pdf/2309.12807.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mortensen, A B, Pedersen, E T, Vives Benedicto, L, Burg, L, Madsen, M R & B\u00f8gh, S 2023 'Teacher-Student Reinforcement Learning for Mapless Navigation using a Planetary Space Rover' arXiv. https://doi.org/10.48550/arXiv.2309.12807","raw_type":"workingPaper"},{"id":"doi:10.48550/arxiv.2309.12807","doi":"https://doi.org/10.48550/arxiv.2309.12807","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.12807","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.12807","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.12807","pdf_url":"https://arxiv.org/pdf/2309.12807","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality education","score":0.5385000109672546,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387031540.pdf","grobid_xml":"https://content.openalex.org/works/W4387031540.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4402904100","https://openalex.org/W7140148389","https://openalex.org/W7102328904","https://openalex.org/W7223055369","https://openalex.org/W7161579157","https://openalex.org/W7140145776","https://openalex.org/W4402904099","https://openalex.org/W3213206045","https://openalex.org/W3180010323","https://openalex.org/W7141592408"],"abstract_inverted_index":{"We":[0,105],"address":[1],"the":[2,55,59,72,126,139,150,174],"challenge":[3],"of":[4,18,74],"enhancing":[5],"navigation":[6,25,76,93],"autonomy":[7,37],"for":[8,27,168],"planetary":[9],"space":[10,20],"rovers":[11,28],"using":[12,112],"reinforcement":[13],"learning":[14,122],"(RL).":[15],"The":[16,66,131],"ambition":[17],"future":[19],"missions":[21],"necessitates":[22],"advanced":[23],"autonomous":[24],"capabilities":[26],"to":[29,50,63,98,148,157,164],"meet":[30],"mission":[31],"objectives.":[32],"RL's":[33],"potential":[34],"in":[35,71,136],"robotic":[36],"is":[38,69,134,142],"evident,":[39],"but":[40],"its":[41],"reliance":[42],"on":[43,77,144],"simulations":[44],"poses":[45],"a":[46,89,95,107,119,165],"challenge.":[47],"Transferring":[48],"policies":[49,161,178],"real-world":[51,102,158,169],"scenarios":[52],"often":[53],"encounters":[54],"\"reality":[56],"gap\",":[57],"disrupting":[58],"transition":[60],"from":[61],"virtual":[62],"physical":[64],"environments.":[65],"reality":[67],"gap":[68],"exacerbated":[70],"context":[73],"mapless":[75],"Mars":[78],"and":[79,85,101,176,190],"Moon-like":[80],"terrains,":[81],"where":[82],"unpredictable":[83],"terrains":[84],"environmental":[86],"factors":[87],"play":[88],"significant":[90],"role.":[91],"Effective":[92],"requires":[94],"method":[96],"attuned":[97],"these":[99],"complexities":[100],"data":[103],"noise.":[104],"introduce":[106],"novel":[108],"two-stage":[109],"RL":[110],"approach":[111,117,182],"offline":[113],"noisy":[114,145],"data.":[115],"Our":[116,160],"employs":[118],"teacher-student":[120],"policy":[121,133,141],"paradigm,":[123],"inspired":[124],"by":[125,128],"\"learning":[127],"cheating\"":[129],"method.":[130],"teacher":[132,175],"trained":[135,143],"simulation.":[137],"Subsequently,":[138],"student":[140,177],"data,":[146],"aiming":[147],"mimic":[149],"teacher's":[151],"behaviors":[152],"while":[153],"being":[154],"more":[155,191],"robust":[156],"uncertainties.":[159],"are":[162],"transferred":[163],"custom-designed":[166],"rover":[167],"testing.":[170],"Comparative":[171],"analyses":[172],"between":[173],"reveal":[179],"that":[180],"our":[181],"offers":[183],"improved":[184],"behavioral":[185],"performance,":[186],"heightened":[187],"noise":[188],"resilience,":[189],"effective":[192],"sim-to-real":[193],"transfer.":[194]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2023-09-26T00:00:00"}