{"id":"https://openalex.org/W3016817194","doi":"https://doi.org/10.1109/icra48506.2021.9560916","title":"Approximate Inverse Reinforcement Learning from Vision-based Imitation Learning","display_name":"Approximate Inverse Reinforcement Learning from Vision-based Imitation Learning","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3016817194","doi":"https://doi.org/10.1109/icra48506.2021.9560916","mag":"3016817194"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9560916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560916","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.08051","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046628126","display_name":"Keuntaek Lee","orcid":"https://orcid.org/0000-0001-5955-5965"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Keuntaek Lee","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology, Atlanta, GA (USA)"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA (USA)","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072885377","display_name":"Bogdan Vlahov","orcid":"https://orcid.org/0000-0003-0224-6664"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bogdan Vlahov","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology, Atlanta, GA (USA)"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA (USA)","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033755663","display_name":"Jason Gibson","orcid":"https://orcid.org/0000-0002-1439-2987"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Gibson","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology, Atlanta, GA (USA)"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA (USA)","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002228469","display_name":"James M. Rehg","orcid":"https://orcid.org/0000-0003-1793-5462"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James M. Rehg","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology, Atlanta, GA (USA)"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA (USA)","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044505993","display_name":"Evangelos A. Theodorou","orcid":"https://orcid.org/0000-0002-0834-5738"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evangelos A. Theodorou","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology, Atlanta, GA (USA)"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA (USA)","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5046628126"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0927,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.36744439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"10793","last_page":"10799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9965000152587891,"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":0.9965000152587891,"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":0.9929999709129333,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9821000099182129,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7436193227767944},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6776961088180542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6654666066169739},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6470987796783447},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5377509593963623},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47152838110923767},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.352382630109787},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12132689356803894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7436193227767944},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6776961088180542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6654666066169739},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6470987796783447},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5377509593963623},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47152838110923767},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.352382630109787},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12132689356803894},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra48506.2021.9560916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560916","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:arXiv.org:2004.08051","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.08051","pdf_url":"https://arxiv.org/pdf/2004.08051","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3016817194","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2004.08051.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2004.08051","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.08051","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.08051","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.08051","pdf_url":"https://arxiv.org/pdf/2004.08051","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"},{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"},{"id":"https://openalex.org/F4320322037","display_name":"Nuclear Safety and Security Commission","ror":"https://ror.org/05qk3ge34"},{"id":"https://openalex.org/F4320332378","display_name":"Langley Research Center","ror":"https://ror.org/0399mhs52"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3016817194.pdf","grobid_xml":"https://content.openalex.org/works/W3016817194.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1527702126","https://openalex.org/W1787224781","https://openalex.org/W2115579991","https://openalex.org/W2119112357","https://openalex.org/W2171455680","https://openalex.org/W2240067561","https://openalex.org/W2296673577","https://openalex.org/W2410617946","https://openalex.org/W2443711627","https://openalex.org/W2559767995","https://openalex.org/W2657631929","https://openalex.org/W2738778707","https://openalex.org/W2806163172","https://openalex.org/W2902276220","https://openalex.org/W2962871846","https://openalex.org/W2967081385","https://openalex.org/W2999729662","https://openalex.org/W3000716014","https://openalex.org/W3007643476","https://openalex.org/W6631190155","https://openalex.org/W6640174482","https://openalex.org/W6685962732","https://openalex.org/W6704559304","https://openalex.org/W6746717651","https://openalex.org/W6752356361","https://openalex.org/W6761342191","https://openalex.org/W7034727938"],"related_works":["https://openalex.org/W3207977358","https://openalex.org/W3101120864","https://openalex.org/W3044004758","https://openalex.org/W3195006999","https://openalex.org/W2959488596","https://openalex.org/W3081866731","https://openalex.org/W3108175278","https://openalex.org/W3175819369","https://openalex.org/W3205868665","https://openalex.org/W3037344895","https://openalex.org/W3186137473","https://openalex.org/W3131040061","https://openalex.org/W1967736575","https://openalex.org/W2967129319","https://openalex.org/W2513584761","https://openalex.org/W3204552159","https://openalex.org/W3017262417","https://openalex.org/W1984935210","https://openalex.org/W2982352566","https://openalex.org/W3151513620"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"present":[4],"a":[5,41,58],"method":[6,101],"for":[7,13,57,74,90],"obtaining":[8],"an":[9,28,52],"implicit":[10],"objective":[11],"function":[12,55],"vision-based":[14,106],"navigation.":[15],"The":[16,62,86],"proposed":[17,87],"methodology":[18],"relies":[19],"on":[20],"Imitation":[21,38],"Learning,":[22],"Model":[23],"Predictive":[24],"Control":[25],"(MPC),":[26],"and":[27,77,93,112,115],"interpretation":[29],"technique":[30],"used":[31,69],"in":[32,48,70,83,109],"Deep":[33],"Neural":[34],"Networks.":[35],"We":[36,98],"use":[37],"Learning":[39,47],"as":[40],"means":[42],"to":[43,50,95,102],"do":[44],"Inverse":[45],"Reinforcement":[46],"order":[49],"create":[51],"approximate":[53],"cost":[54,64],"generator":[56],"visual":[59],"navigation":[60],"challenge.":[61],"resulting":[63],"function,":[65],"the":[66,103],"costmap,":[67],"is":[68],"conjunction":[71],"with":[72],"MPC":[73],"real-time":[75],"control":[76],"outperforms":[78],"other":[79],"state-of-the-art":[80],"costmap":[81],"generators":[82],"novel":[84],"environments.":[85],"process":[88],"allows":[89],"simple":[91],"training":[92],"robustness":[94],"out-of-sample":[96],"data.":[97],"apply":[99],"our":[100],"task":[104],"of":[105],"autonomous":[107],"driving":[108],"multiple":[110],"real":[111],"simulated":[113],"environments":[114],"show":[116],"its":[117],"generalizability.":[118],"Supplementary":[119],"video:":[120],"https://youtu.be/WyJfT5lc0aQ":[121]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}