{"id":"https://openalex.org/W4287509240","doi":"https://doi.org/10.1007/s10514-023-10118-4","title":"Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning","display_name":"Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning","publication_year":2023,"publication_date":"2023-07-06","ids":{"openalex":"https://openalex.org/W4287509240","doi":"https://doi.org/10.1007/s10514-023-10118-4"},"language":"en","primary_location":{"id":"doi:10.1007/s10514-023-10118-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10514-023-10118-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10514-023-10118-4.pdf","source":{"id":"https://openalex.org/S144091109","display_name":"Autonomous Robots","issn_l":"0929-5593","issn":["0929-5593","1573-7527"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Robots","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10514-023-10118-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100417408","display_name":"Tianyu Wang","orcid":"https://orcid.org/0000-0001-6206-8359"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tianyu Wang","raw_affiliation_strings":["Electrical and Computer Engineering, University of California, San Diego, 9500 Gilman Dr, La Jolla, CA, 92093, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of California, San Diego, 9500 Gilman Dr, La Jolla, CA, 92093, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033777391","display_name":"Vikas Dhiman","orcid":"https://orcid.org/0000-0003-0078-3677"},"institutions":[{"id":"https://openalex.org/I7947594","display_name":"University of Maine","ror":"https://ror.org/01adr0w49","country_code":"US","type":"education","lineage":["https://openalex.org/I2802397601","https://openalex.org/I7947594"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikas Dhiman","raw_affiliation_strings":["Electrical and Computer Engineering, The University of Maine, 168 College Ave, Orono, ME, 04469, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, The University of Maine, 168 College Ave, Orono, ME, 04469, USA","institution_ids":["https://openalex.org/I7947594"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066400889","display_name":"Nikolay Atanasov","orcid":"https://orcid.org/0000-0003-0272-7580"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolay Atanasov","raw_affiliation_strings":["Electrical and Computer Engineering, University of California, San Diego, 9500 Gilman Dr, La Jolla, CA, 92093, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of California, San Diego, 9500 Gilman Dr, La Jolla, CA, 92093, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100417408"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":{"value":2590,"currency":"EUR","value_usd":3390},"apc_paid":{"value":2590,"currency":"EUR","value_usd":3390},"fwci":0.8757,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77279522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"47","issue":"6","first_page":"809","last_page":"830"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9993000030517578,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9980000257492065,"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":0.8595841526985168},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6712628602981567},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.6070852875709534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6026490926742554},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5974748730659485},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5175027847290039},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.47450774908065796},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4726511538028717},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4436373710632324},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4314475655555725},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.4290541410446167},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.22434544563293457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8595841526985168},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6712628602981567},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.6070852875709534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6026490926742554},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5974748730659485},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5175027847290039},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.47450774908065796},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4726511538028717},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4436373710632324},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4314475655555725},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.4290541410446167},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.22434544563293457},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10514-023-10118-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10514-023-10118-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10514-023-10118-4.pdf","source":{"id":"https://openalex.org/S144091109","display_name":"Autonomous Robots","issn_l":"0929-5593","issn":["0929-5593","1573-7527"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Robots","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10514-023-10118-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10514-023-10118-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10514-023-10118-4.pdf","source":{"id":"https://openalex.org/S144091109","display_name":"Autonomous Robots","issn_l":"0929-5593","issn":["0929-5593","1573-7527"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Robots","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4287509240.pdf"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1591675293","https://openalex.org/W1836465849","https://openalex.org/W1837766154","https://openalex.org/W1931877416","https://openalex.org/W1971086298","https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2054389289","https://openalex.org/W2098432798","https://openalex.org/W2098774185","https://openalex.org/W2116442740","https://openalex.org/W2117675763","https://openalex.org/W2133844819","https://openalex.org/W2161395589","https://openalex.org/W2169498096","https://openalex.org/W2181095272","https://openalex.org/W2221898772","https://openalex.org/W2290104316","https://openalex.org/W2336416123","https://openalex.org/W2593841437","https://openalex.org/W2594103415","https://openalex.org/W2607968634","https://openalex.org/W2769520592","https://openalex.org/W2890003176","https://openalex.org/W2962912109","https://openalex.org/W2962951365","https://openalex.org/W2963125977","https://openalex.org/W2963411833","https://openalex.org/W2963713397","https://openalex.org/W2963881378","https://openalex.org/W2964128312","https://openalex.org/W2964309882","https://openalex.org/W2970971581","https://openalex.org/W2973181288","https://openalex.org/W2979863294","https://openalex.org/W2980192220","https://openalex.org/W2988072049","https://openalex.org/W2990138404","https://openalex.org/W2999344697","https://openalex.org/W3003437478","https://openalex.org/W3006303816","https://openalex.org/W3021208093","https://openalex.org/W3091379283","https://openalex.org/W3093434340","https://openalex.org/W3093784762","https://openalex.org/W3102129812","https://openalex.org/W3182474098","https://openalex.org/W4211092921","https://openalex.org/W6631190155","https://openalex.org/W6632235069","https://openalex.org/W6674995601","https://openalex.org/W6682849425","https://openalex.org/W6683620479","https://openalex.org/W6694954494","https://openalex.org/W6703161083","https://openalex.org/W6718092244","https://openalex.org/W6730267373","https://openalex.org/W6743790455","https://openalex.org/W6745935785","https://openalex.org/W6746136750"],"related_works":["https://openalex.org/W4285277090","https://openalex.org/W4327738859","https://openalex.org/W2348722996","https://openalex.org/W2334570605","https://openalex.org/W3181683615","https://openalex.org/W4286826125","https://openalex.org/W1633485514","https://openalex.org/W1980454230","https://openalex.org/W2300851791","https://openalex.org/W1604739066"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"focuses":[3],"on":[4,32,176],"inverse":[5],"reinforcement":[6],"learning":[7],"for":[8],"autonomous":[9,170],"navigation":[10],"using":[11,110],"distance":[12],"and":[13,36,53,89,182],"semantic":[14,46,65,143,177],"category":[15,47],"observations.":[16],"The":[17],"objective":[18],"is":[19,71],"to":[20,134,164],"infer":[21],"a":[22,41,54,59,90,100,111,117,123,154],"cost":[23,55,70,96],"function":[24],"that":[25,44,106,160],"explains":[26],"demonstrated":[27,87],"behavior":[28,105,133],"while":[29],"relying":[30,175],"only":[31,79,115],"the":[33,50,64,68,75,84,95,131,142,147,169],"expert\u2019s":[34],"observations":[35,178],"state-control":[37],"trajectory.":[38],"We":[39,98,145,157],"develop":[40],"map":[42],"encoder,":[43,56],"infers":[45],"probabilities":[48],"from":[49,94],"observation":[51],"sequence,":[52],"defined":[57],"as":[58],"deep":[60],"neural":[61],"network":[62],"over":[63,116],"features.":[66],"Since":[67],"expert":[69,104],"not":[72],"directly":[73],"observable,":[74],"model":[76,102,152],"parameters":[77],"can":[78],"be":[80],"optimized":[81],"by":[82,174],"differentiating":[83],"error":[85,108],"between":[86],"controls":[88],"control":[91],"policy":[92],"computed":[93,114],"estimate.":[97],"propose":[99],"new":[101,135,138],"of":[103,119,141,150,179],"enables":[107],"minimization":[109],"closed-form":[112],"subgradient":[113],"subset":[118],"promising":[120],"states":[121],"via":[122],"motion":[124],"planning":[125],"algorithm.":[126],"Our":[127],"approach":[128,162],"allows":[129],"generalizing":[130],"learned":[132],"environments":[136],"with":[137],"spatial":[139],"configurations":[140],"categories.":[144],"analyze":[146],"different":[148],"components":[149],"our":[151,161],"in":[153,168],"minigrid":[155],"environment.":[156],"also":[158],"demonstrate":[159],"learns":[163],"follow":[165],"traffic":[166],"rules":[167],"driving":[171],"CARLA":[172],"simulator":[173],"buildings,":[180],"sidewalks,":[181],"road":[183],"lanes.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-01-23T23:20:30.427331","created_date":"2025-10-10T00:00:00"}