{"id":"https://openalex.org/W7213596702","doi":"https://doi.org/10.48550/arxiv.2609.20747","title":"MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving","display_name":"MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving","publication_year":2026,"publication_date":"2026-09-17","ids":{"openalex":"https://openalex.org/W7213596702","doi":"https://doi.org/10.48550/arxiv.2609.20747"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.20747","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20747","pdf_url":"https://arxiv.org/pdf/2609.20747","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.20747","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033799649","display_name":"Thomas Steinecker","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40527276","display_name":"Universit\u00e4t der Bundeswehr M\u00fcnchen","ror":"https://ror.org/05kkv3f82","country_code":"DE","type":"education","lineage":["https://openalex.org/I1315109972","https://openalex.org/I40527276","https://openalex.org/I4387152969"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steinecker, Thomas","raw_affiliation_strings":["Chair of Machine Perception for Autonomous Driving , University of the Bundeswehr Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Machine Perception for Autonomous Driving , University of the Bundeswehr Munich , Germany","institution_ids":["https://openalex.org/I40527276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119487712","display_name":"Denis Trescher","orcid":"https://orcid.org/0009-0008-0939-9317","observed_orcids":["https://orcid.org/0009-0008-0939-9317"]},"institutions":[{"id":"https://openalex.org/I40527276","display_name":"Universit\u00e4t der Bundeswehr M\u00fcnchen","ror":"https://ror.org/05kkv3f82","country_code":"DE","type":"education","lineage":["https://openalex.org/I1315109972","https://openalex.org/I40527276","https://openalex.org/I4387152969"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Trescher, Denis","raw_affiliation_strings":["Chair of Machine Perception for Autonomous Driving , University of the Bundeswehr Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Machine Perception for Autonomous Driving , University of the Bundeswehr Munich , Germany","institution_ids":["https://openalex.org/I40527276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022985130","display_name":"Alexander Bienemann","orcid":"https://orcid.org/0009-0007-4773-5724","observed_orcids":["https://orcid.org/0009-0007-4773-5724"]},"institutions":[{"id":"https://openalex.org/I40527276","display_name":"Universit\u00e4t der Bundeswehr M\u00fcnchen","ror":"https://ror.org/05kkv3f82","country_code":"DE","type":"education","lineage":["https://openalex.org/I1315109972","https://openalex.org/I40527276","https://openalex.org/I4387152969"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bienemann, Alexander","raw_affiliation_strings":["Chair of Machine Perception for Autonomous Driving , University of the Bundeswehr Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Machine Perception for Autonomous Driving , University of the Bundeswehr Munich , Germany","institution_ids":["https://openalex.org/I40527276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016189127","display_name":"Thorsten Luettel","orcid":"https://orcid.org/0000-0002-7047-8179","observed_orcids":["https://orcid.org/0000-0002-7047-8179"]},"institutions":[{"id":"https://openalex.org/I40527276","display_name":"Universit\u00e4t der Bundeswehr M\u00fcnchen","ror":"https://ror.org/05kkv3f82","country_code":"DE","type":"education","lineage":["https://openalex.org/I1315109972","https://openalex.org/I40527276","https://openalex.org/I4387152969"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Luettel, Thorsten","raw_affiliation_strings":["Chair of Machine Perception for Autonomous Driving , University of the Bundeswehr Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Machine Perception for Autonomous Driving , University of the Bundeswehr Munich , Germany","institution_ids":["https://openalex.org/I40527276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5096114072","display_name":"Mirko Maehlisch","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40527276","display_name":"Universit\u00e4t der Bundeswehr M\u00fcnchen","ror":"https://ror.org/05kkv3f82","country_code":"DE","type":"education","lineage":["https://openalex.org/I1315109972","https://openalex.org/I40527276","https://openalex.org/I4387152969"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maehlisch, Mirko","raw_affiliation_strings":["Chair of Machine Perception for Autonomous Driving , University of the Bundeswehr Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Machine Perception for Autonomous Driving , University of the Bundeswehr Munich , Germany","institution_ids":["https://openalex.org/I40527276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40527276"],"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":0.9086999893188477,"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":0.9086999893188477,"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":0.08980000019073486,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0003000000142492354,"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/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.9610000252723694},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.8679999709129333},{"id":"https://openalex.org/keywords/unstructured-environments","display_name":"unstructured environments","score":0.7379999756813049},{"id":"https://openalex.org/keywords/zero-shot-transfer","display_name":"zero-shot transfer","score":0.6549999713897705},{"id":"https://openalex.org/keywords/trajectory-alignment","display_name":"trajectory alignment","score":0.8700000047683716},{"id":"https://openalex.org/keywords/bicycle-model","display_name":"bicycle model","score":0.7450000047683716},{"id":"https://openalex.org/keywords/off-road-driving","display_name":"off-road driving","score":0.7289999723434448},{"id":"https://openalex.org/keywords/jetson-agx-orin","display_name":"Jetson AGX Orin","score":0.7950000166893005}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8779000043869019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757099986076355},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5989000201225281},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5985000133514404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.541100025177002},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4918999969959259},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4902999997138977},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3856000006198883},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C2779178101","wikidata":"https://www.wikidata.org/wiki/Q6987274","display_name":"Negative transfer","level":3,"score":0.3596999943256378},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C80519477","wikidata":"https://www.wikidata.org/wiki/Q3532236","display_name":"Scenario testing","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.258899986743927},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.20747","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20747","pdf_url":"https://arxiv.org/pdf/2609.20747","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.20747","doi":"https://doi.org/10.48550/arxiv.2609.20747","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.20747","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:2609.20747","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20747","pdf_url":"https://arxiv.org/pdf/2609.20747","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5378999710083008}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320317352","display_name":"Bundesamt f\u00fcr Ausr\u00fcstung, Informationstechnik und Nutzung der Bundeswehr","ror":"https://ror.org/026sbm463"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F7311471023","display_name":"NextGenerationEU","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213596702.pdf","grobid_xml":"https://content.openalex.org/works/W7213596702.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W2806163172","https://openalex.org/W4224314580","https://openalex.org/W4327810158","https://openalex.org/W4394867415","https://openalex.org/W4416158863","https://openalex.org/W7134226850"],"related_works":["https://openalex.org/W7151398042","https://openalex.org/W4286783977","https://openalex.org/W4307478166","https://openalex.org/W7212052045","https://openalex.org/W3186212639","https://openalex.org/W2952056562","https://openalex.org/W7214368297","https://openalex.org/W2782851602","https://openalex.org/W4416049998","https://openalex.org/W2920980023"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"constitutes":[2],"a":[3,59,81,100,129,149,181,203],"promising":[4],"approach":[5],"owing":[6],"to":[7,19,80,98,122,164],"its":[8,17,75],"potential":[9],"for":[10,37],"superhuman":[11],"performance":[12],"and":[13,66,91,140,167],"self-learned":[14],"policies.":[15],"However,":[16],"application":[18],"real-world":[20],"autonomous":[21],"driving":[22],"remains":[23],"scarce,":[24],"particularly":[25],"in":[26],"unstructured":[27,38],"environments,":[28],"because":[29],"of":[30,107,137,162,193],"the":[31,68,87,108,115,123,145,191,197],"challenges":[32],"associated":[33],"with":[34,50,74,105,176],"sim-to-real":[35,52,135],"transfer":[36,136],"environments.":[39],"In":[40,170],"this":[41],"work,":[42],"we":[43,57,127,172],"present":[44],"MILER,":[45],"an":[46],"end-to-end":[47],"policy":[48,69,116],"framework":[49,147],"zero-shot":[51,134],"transfer.":[53],"During":[54,84],"offline":[55],"training,":[56],"employ":[58,128],"custom":[60],"semantic":[61,101],"mid-level":[62],"representation":[63,103],"(MLR)":[64],"simulator":[65],"train":[67],"network":[70,117],"using":[71],"reinforcement":[72],"learning,":[73],"control":[76],"outputs":[77],"applied":[78,120],"directly":[79,121],"bicycle":[82],"model.":[83],"deployment":[85],"on":[86,148,180,202],"real":[88,124],"vehicle,":[89],"camera":[90],"LiDAR":[92],"data":[93],"are":[94,118],"processed":[95],"by":[96,114],"BEVFusion":[97],"generate":[99],"bird's-eye-view":[102],"consistent":[104],"that":[106,132],"MLR":[109],"simulator.":[110],"The":[111],"actions":[112],"generated":[113],"not":[119],"vehicle.":[125],"Instead,":[126],"trajectory-alignment":[130],"strategy":[131],"enables":[133],"both":[138],"perception":[139],"control.":[141],"We":[142],"extensively":[143],"evaluate":[144],"proposed":[146],"diverse":[150],"test":[151,184],"track":[152,185],"comprising":[153],"numerous":[154],"challenges,":[155],"including":[156],"various":[157],"obstacles,":[158],"hairpin":[159],"curves,":[160],"velocities":[161],"up":[163],"33.6":[165],"km/h,":[166],"off-road":[168],"sections.":[169],"total,":[171],"drove":[173],"17.3":[174],"km":[175,183],"two":[177],"different":[178],"vehicles":[179],"3.0":[182],"without":[186],"human":[187],"intervention,":[188],"thereby":[189],"demonstrating":[190],"effectiveness":[192],"our":[194],"approach.":[195],"Furthermore,":[196],"entire":[198],"software":[199],"stack":[200],"runs":[201],"Jetson":[204],"AGX":[205],"Orin.":[206]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-19T00:00:00"}