{"id":"https://openalex.org/W3206298348","doi":"https://doi.org/10.1109/icra48506.2021.9560907","title":"Decision Making for Autonomous Driving via Augmented Adversarial Inverse Reinforcement Learning","display_name":"Decision Making for Autonomous Driving via Augmented Adversarial Inverse Reinforcement Learning","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3206298348","doi":"https://doi.org/10.1109/icra48506.2021.9560907","mag":"3206298348"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9560907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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/A5100735652","display_name":"Pin Wang","orcid":"https://orcid.org/0000-0002-1400-4497"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pin Wang","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693875","display_name":"Dapeng Liu","orcid":"https://orcid.org/0000-0002-8822-656X"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Dapeng Liu","raw_affiliation_strings":["Zenseact, Chalmers University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zenseact, Chalmers University of Technology","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380049","display_name":"Jiayu Chen","orcid":"https://orcid.org/0000-0002-7708-5247"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayu Chen","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060703637","display_name":"Hanhan Li","orcid":"https://orcid.org/0000-0002-6844-7314"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanhan Li","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014661259","display_name":"Ching\u2010Yao Chan","orcid":"https://orcid.org/0000-0003-3992-2312"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ching-Yao Chan","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.0843,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.9923253,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1036","last_page":"1042"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9988999962806702,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9968000054359436,"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/adversarial-system","display_name":"Adversarial system","score":0.8322073221206665},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.773363471031189},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6787658333778381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4785345494747162},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.43466493487358093},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.343514621257782},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1025199294090271}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8322073221206665},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.773363471031189},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6787658333778381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4785345494747162},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.43466493487358093},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.343514621257782},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1025199294090271},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra48506.2021.9560907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:research.chalmers.se:528998","is_oa":false,"landing_page_url":"https://research.chalmers.se/en/publication/528998","pdf_url":null,"source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"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}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W64088143","https://openalex.org/W1516447630","https://openalex.org/W1527702126","https://openalex.org/W1771410628","https://openalex.org/W1777239053","https://openalex.org/W1949804828","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2104733512","https://openalex.org/W2173248099","https://openalex.org/W2283952362","https://openalex.org/W2290104316","https://openalex.org/W2530849036","https://openalex.org/W2566467060","https://openalex.org/W2580495915","https://openalex.org/W2736791111","https://openalex.org/W2938421504","https://openalex.org/W2949916679","https://openalex.org/W2962879692","https://openalex.org/W2963277051","https://openalex.org/W2963322416","https://openalex.org/W2963508354","https://openalex.org/W2963590100","https://openalex.org/W2963864421","https://openalex.org/W2970065535","https://openalex.org/W2990380406","https://openalex.org/W4256152864","https://openalex.org/W4256153703","https://openalex.org/W4295521014","https://openalex.org/W4301501993","https://openalex.org/W6638018090","https://openalex.org/W6638088447","https://openalex.org/W6674884181","https://openalex.org/W6675999342","https://openalex.org/W6684921986","https://openalex.org/W6696380822","https://openalex.org/W6718092244","https://openalex.org/W6731259203","https://openalex.org/W6735913928","https://openalex.org/W6745347688","https://openalex.org/W6763952582","https://openalex.org/W6903351479"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"Making":[0],"decisions":[1],"in":[2,54,79,97,102],"complex":[3],"driving":[4],"environments":[5,58],"is":[6,29,51,108,134],"a":[7,22,41,45,90,98],"challenging":[8,94],"task":[9,96],"for":[10,19],"autonomous":[11,103],"agents.":[12],"Imitation":[13],"learning":[14,35,81],"methods":[15,36],"have":[16],"great":[17],"potentials":[18],"achieving":[20],"such":[21],"goal.":[23],"Adversarial":[24],"Inverse":[25],"Reinforcement":[26],"Learning":[27],"(AIRL)":[28],"one":[30],"of":[31,138,143],"the":[32,80,86,123,128,139,144],"state-of-art":[33],"imitation":[34],"that":[37,122,137],"can":[38],"learn":[39],"both":[40],"behavioral":[42],"policy":[43],"and":[44,56,69,93,113,131],"reward":[46],"function":[47],"simultaneously,":[48],"yet":[49],"it":[50,75],"only":[52],"demonstrated":[53],"simple":[55],"static":[57],"where":[59],"no":[60],"interactions":[61],"are":[62],"introduced.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,84],"improve":[68],"stabilize":[70],"AIRL’s":[71],"performance":[72,117,133],"by":[73,115],"augmenting":[74],"with":[76,110,136],"semantic":[77],"rewards":[78],"framework.":[82],"Additionally,":[83],"adapt":[85],"augmented":[87,124],"AIRL":[88,125],"to":[89],"more":[91],"practical":[92],"decision-making":[95],"highly":[99],"interactive":[100],"environment":[101],"driving.":[104],"The":[105],"proposed":[106],"method":[107],"compared":[109],"four":[111,116,145],"baselines":[112],"evaluated":[114],"metrics.":[118,146],"Simulation":[119],"results":[120],"show":[121],"outperforms":[126],"all":[127,142],"baseline":[129],"methods,":[130],"its":[132],"comparable":[135],"experts":[140],"on":[141]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}