{"id":"https://openalex.org/W4285813059","doi":"https://doi.org/10.1109/iv51971.2022.9827031","title":"Learning Reward Models for Cooperative Trajectory Planning with Inverse Reinforcement Learning and Monte Carlo Tree Search","display_name":"Learning Reward Models for Cooperative Trajectory Planning with Inverse Reinforcement Learning and Monte Carlo Tree Search","publication_year":2022,"publication_date":"2022-06-05","ids":{"openalex":"https://openalex.org/W4285813059","doi":"https://doi.org/10.1109/iv51971.2022.9827031"},"language":"en","primary_location":{"id":"doi:10.1109/iv51971.2022.9827031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv51971.2022.9827031","pdf_url":null,"source":{"id":"https://openalex.org/S4363605370","display_name":"2022 IEEE Intelligent Vehicles Symposium (IV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},"type":"article","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/A5036105953","display_name":"Karl Kurzer","orcid":"https://orcid.org/0000-0003-1556-8232"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Karl Kurzer","raw_affiliation_strings":["Institute of Applied Informatics and Formal Description Methods, Karlsruhe Institute of Technology,Karlsruhe,Germany,76131"],"affiliations":[{"raw_affiliation_string":"Institute of Applied Informatics and Formal Description Methods, Karlsruhe Institute of Technology,Karlsruhe,Germany,76131","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007323139","display_name":"Matthias Bitzer","orcid":null},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Bitzer","raw_affiliation_strings":["Bosch Center for Artificial Intelligence, Robert Bosch GmbH,Renningen,Germany,71272"],"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence, Robert Bosch GmbH,Renningen,Germany,71272","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060028048","display_name":"J. Marius Z\u00f6llner","orcid":"https://orcid.org/0000-0001-6190-7202"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J. Marius Zollner","raw_affiliation_strings":["Institute of Applied Informatics and Formal Description Methods, Karlsruhe Institute of Technology,Karlsruhe,Germany,76131"],"affiliations":[{"raw_affiliation_string":"Institute of Applied Informatics and Formal Description Methods, Karlsruhe Institute of Technology,Karlsruhe,Germany,76131","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036105953"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":0.8315,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73863392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"22","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9934999942779541,"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":0.9934999942779541,"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":0.9921000003814697,"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":0.98580002784729,"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/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.8218849897384644},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.702182948589325},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.668688178062439},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.6090612411499023},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5918130874633789},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5818382501602173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49472686648368835},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4652940034866333},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37948012351989746},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37206751108169556},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1977730393409729},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09155264496803284},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06145888566970825},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.061401814222335815}],"concepts":[{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.8218849897384644},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.702182948589325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.668688178062439},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.6090612411499023},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5918130874633789},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5818382501602173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49472686648368835},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4652940034866333},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37948012351989746},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37206751108169556},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1977730393409729},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09155264496803284},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06145888566970825},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.061401814222335815},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iv51971.2022.9827031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv51971.2022.9827031","pdf_url":null,"source":{"id":"https://openalex.org/S4363605370","display_name":"2022 IEEE Intelligent Vehicles Symposium (IV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1527702126","https://openalex.org/W1929981607","https://openalex.org/W1999874108","https://openalex.org/W2098774185","https://openalex.org/W2145339207","https://openalex.org/W2290104316","https://openalex.org/W2890375627","https://openalex.org/W2949556825","https://openalex.org/W2962951365","https://openalex.org/W3037606473","https://openalex.org/W3091165146","https://openalex.org/W3100247915","https://openalex.org/W3104559688","https://openalex.org/W3138984732","https://openalex.org/W3210614280","https://openalex.org/W6640443443","https://openalex.org/W6674884181","https://openalex.org/W6696380822"],"related_works":["https://openalex.org/W2571592646","https://openalex.org/W4247855592","https://openalex.org/W2567165815","https://openalex.org/W2740304877","https://openalex.org/W2978000411","https://openalex.org/W4306904969","https://openalex.org/W4226164546","https://openalex.org/W2766259847","https://openalex.org/W2112583639","https://openalex.org/W3136325136"],"abstract_inverted_index":{"Cooperative":[0],"trajectory":[1],"planning":[2],"methods":[3],"for":[4,22],"automated":[5,31],"vehicles":[6],"can":[7,39,103],"solve":[8],"traffic":[9,19],"scenarios":[10],"that":[11,37,64,87,100,109],"require":[12],"a":[13,61,105,117],"high":[14],"degree":[15],"of":[16,91],"cooperation":[17],"between":[18],"participants.":[20],"However,":[21],"cooperative":[23,94],"systems":[24,32],"to":[25,59,83,116],"integrate":[26],"into":[27],"human-centered":[28],"traffic,":[29],"the":[30,41,53,89,101,111],"must":[33],"behave":[34],"human-like":[35],"so":[36],"humans":[38],"anticipate":[40],"system\u2019s":[42],"decisions.":[43],"While":[44],"Reinforcement":[45,75],"Learning":[46,76],"has":[47],"made":[48],"remarkable":[49],"progress":[50],"in":[51],"solving":[52],"decision-making":[54],"part,":[55],"it":[56],"is":[57],"non-trivial":[58],"parameterize":[60],"reward":[62,85,107,121],"model":[63,108],"yields":[65],"predictable":[66],"actions.":[67],"This":[68],"work":[69],"employs":[70],"feature-based":[71],"Maximum":[72],"Entropy":[73],"Inverse":[74],"combined":[77],"with":[78],"Monte":[79],"Carlo":[80],"Tree":[81],"Search":[82],"learn":[84],"models":[86],"maximize":[88],"likelihood":[90],"recorded":[92],"multi-agent":[93],"expert":[95,112],"trajectories.":[96],"The":[97],"evaluation":[98],"demonstrates":[99],"approach":[102],"recover":[104],"reasonable":[106],"mimics":[110],"and":[113],"performs":[114],"similarly":[115],"manually":[118],"tuned":[119],"baseline":[120],"model.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}