{"id":"https://openalex.org/W3181452220","doi":"https://doi.org/10.1109/iros51168.2021.9635935","title":"Reinforcement Learning based Negotiation-aware Motion Planning of Autonomous Vehicles","display_name":"Reinforcement Learning based Negotiation-aware Motion Planning of Autonomous Vehicles","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3181452220","doi":"https://doi.org/10.1109/iros51168.2021.9635935","mag":"3181452220"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9635935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9635935","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5100682838","display_name":"Zhitao Wang","orcid":"https://orcid.org/0000-0002-8552-3657"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhitao Wang","raw_affiliation_strings":["Noah\u2019s Ark Lab, Huawei Technologies, Beijing, China","Noah's Ark Lab, Huawei Technologies, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Noah\u2019s Ark Lab, Huawei Technologies, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei Technologies, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011036128","display_name":"Yuzheng Zhuang","orcid":"https://orcid.org/0000-0002-0915-0254"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzheng Zhuang","raw_affiliation_strings":["Noah\u2019s Ark Lab, Huawei Technologies, Beijing, China","Noah's Ark Lab, Huawei Technologies, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Noah\u2019s Ark Lab, Huawei Technologies, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei Technologies, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014261059","display_name":"Qiang Gu","orcid":"https://orcid.org/0000-0002-2606-0461"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Gu","raw_affiliation_strings":["Noah\u2019s Ark Lab, Huawei Technologies, Beijing, China","Noah's Ark Lab, Huawei Technologies, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Noah\u2019s Ark Lab, Huawei Technologies, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei Technologies, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319453","display_name":"Dong Chen","orcid":"https://orcid.org/0000-0002-0551-5084"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Chen","raw_affiliation_strings":["Noah\u2019s Ark Lab, Huawei Technologies, Beijing, China","Noah's Ark Lab, Huawei Technologies, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Noah\u2019s Ark Lab, Huawei Technologies, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei Technologies, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461116","display_name":"Hongbo Zhang","orcid":"https://orcid.org/0009-0005-8753-2580"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Zhang","raw_affiliation_strings":["Noah\u2019s Ark Lab, Huawei Technologies, Beijing, China","Noah's Ark Lab, Huawei Technologies, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Noah\u2019s Ark Lab, Huawei Technologies, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei Technologies, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036527488","display_name":"Wulong Liu","orcid":"https://orcid.org/0000-0003-2901-1523"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wulong Liu","raw_affiliation_strings":["Noah\u2019s Ark Lab, Huawei Technologies, Beijing, China","Noah's Ark Lab, Huawei Technologies, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Noah\u2019s Ark Lab, Huawei Technologies, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei Technologies, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100682838"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":2.2177,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.91605456,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4532","last_page":"4537"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9988999962806702,"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/T10524","display_name":"Traffic control and management","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8551198244094849},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7549352645874023},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6624194979667664},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.5681554079055786},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5610482692718506},{"id":"https://openalex.org/keywords/negotiation","display_name":"Negotiation","score":0.548169732093811},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5469560623168945},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5446187853813171},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5189387798309326},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4104204773902893},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4088178277015686},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37869691848754883},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3776538670063019},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.33539652824401855},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.17542752623558044}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8551198244094849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7549352645874023},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6624194979667664},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.5681554079055786},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5610482692718506},{"id":"https://openalex.org/C199776023","wikidata":"https://www.wikidata.org/wiki/Q202875","display_name":"Negotiation","level":2,"score":0.548169732093811},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5469560623168945},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5446187853813171},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5189387798309326},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4104204773902893},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4088178277015686},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37869691848754883},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3776538670063019},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.33539652824401855},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.17542752623558044},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros51168.2021.9635935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9635935","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W101508493","https://openalex.org/W2038705758","https://openalex.org/W2101008389","https://openalex.org/W2107338474","https://openalex.org/W2121806728","https://openalex.org/W2124595631","https://openalex.org/W2124651605","https://openalex.org/W2145339207","https://openalex.org/W2192586580","https://openalex.org/W2257979135","https://openalex.org/W2296073425","https://openalex.org/W2344985987","https://openalex.org/W2404189583","https://openalex.org/W2482772985","https://openalex.org/W2514762535","https://openalex.org/W2583993537","https://openalex.org/W2739770424","https://openalex.org/W2741086815","https://openalex.org/W2749928749","https://openalex.org/W2758107681","https://openalex.org/W2783963507","https://openalex.org/W2884634491","https://openalex.org/W2886763004","https://openalex.org/W2901633079","https://openalex.org/W2905173465","https://openalex.org/W2942735643","https://openalex.org/W2962721463","https://openalex.org/W2964136016","https://openalex.org/W2968008415","https://openalex.org/W2989958156","https://openalex.org/W2990116160","https://openalex.org/W3100944043","https://openalex.org/W3104181348","https://openalex.org/W6678541622","https://openalex.org/W6743802245","https://openalex.org/W6756429999","https://openalex.org/W6756871163","https://openalex.org/W6767069752","https://openalex.org/W6769979845"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2160491016","https://openalex.org/W2294884454","https://openalex.org/W4323315247","https://openalex.org/W3169161914"],"abstract_inverted_index":{"For":[0],"autonomous":[1,68],"vehicles":[2],"integrating":[3],"onto":[4],"road-ways":[5],"with":[6,148],"human":[7],"traffic":[8,72],"participants,":[9],"it":[10],"requires":[11],"understanding":[12],"and":[13,70,108,125],"adapting":[14],"to":[15,38,93,103,118,128,139],"the":[16,40,44,49,54,64,67,105,109,112,131,135,144],"participants\u2019":[17],"intention":[18,97],"by":[19,46],"responding":[20],"in":[21,57,122,142],"predictable":[22],"ways.":[23],"This":[24],"paper":[25],"proposes":[26],"a":[27,75],"reinforcement":[28],"learning":[29,100],"based":[30],"negotiation-aware":[31],"motion":[32,55],"planning":[33],"framework,":[34],"which":[35],"adopts":[36],"RL":[37,91],"adjust":[39],"driving":[41],"style":[42],"of":[43,53,82,111],"planner":[45,56],"dynamically":[47],"modifying":[48],"prediction":[50],"horizon":[51],"length":[52],"real":[58,126],"time":[59],"adaptively.":[60],"The":[61],"framework":[62],"models":[63],"interaction":[65],"between":[66],"vehicle":[69],"other":[71],"participants":[73],"as":[74,88],"Markov":[76],"Decision":[77],"Process.":[78],"A":[79],"temporal":[80],"sequence":[81],"occupancy":[83],"grid":[84],"maps":[85],"are":[86],"taken":[87],"inputs":[89],"for":[90],"module":[92],"embed":[94],"an":[95],"implicit":[96],"reasoning.":[98],"Curriculum":[99],"is":[101],"employed":[102],"enhance":[104],"training":[106],"efficiency":[107],"robustness":[110],"algorithm.":[113],"We":[114],"applied":[115],"our":[116],"method":[117,133],"narrow":[119],"lane":[120],"navigation":[121],"both":[123],"simulation":[124],"world":[127],"demonstrate":[129],"that":[130],"proposed":[132],"outperforms":[134],"common":[136],"alternative":[137],"due":[138],"its":[140],"advantage":[141],"alleviating":[143],"social":[145],"dilemma":[146],"problem":[147],"proper":[149],"negotiation":[150],"skills.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}