{"id":"https://openalex.org/W4405787345","doi":"https://doi.org/10.1109/iros58592.2024.10801688","title":"Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning","display_name":"Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405787345","doi":"https://doi.org/10.1109/iros58592.2024.10801688"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5001116971","display_name":"Mirco Theile","orcid":"https://orcid.org/0000-0003-1574-8858"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Mirco Theile","raw_affiliation_strings":["Technical University of Munich,TUM School of Engineering and Design,Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,TUM School of Engineering and Design,Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030370370","display_name":"Hongpeng Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hongpeng Cao","raw_affiliation_strings":["Technical University of Munich,TUM School of Engineering and Design,Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,TUM School of Engineering and Design,Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060442004","display_name":"Marco Caccamo","orcid":"https://orcid.org/0000-0003-2328-044X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marco Caccamo","raw_affiliation_strings":["Technical University of Munich,TUM School of Engineering and Design,Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,TUM School of Engineering and Design,Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088660554","display_name":"Alberto Sangiovanni\u2010Vincentelli","orcid":"https://orcid.org/0000-0003-1298-8389"},"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":"Alberto L. Sangiovanni-Vincentelli","raw_affiliation_strings":["University of California,Dept. of Electrical Engineering and Computer Sciences,Berkeley,USA"],"affiliations":[{"raw_affiliation_string":"University of California,Dept. of Electrical Engineering and Computer Sciences,Berkeley,USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001116971"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58158042,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"14164","last_page":"14171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T11615","display_name":"Control and Dynamics of Mobile Robots","score":0.989799976348877,"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":0.8057690858840942},{"id":"https://openalex.org/keywords/equivariant-map","display_name":"Equivariant map","score":0.733019232749939},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6233495473861694},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6026212573051453},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.57399582862854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4715701937675476},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.41692090034484863},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32396090030670166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2499294877052307},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09829151630401611},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.07381704449653625},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.06050571799278259}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8057690858840942},{"id":"https://openalex.org/C171036898","wikidata":"https://www.wikidata.org/wiki/Q256355","display_name":"Equivariant map","level":2,"score":0.733019232749939},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6233495473861694},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6026212573051453},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.57399582862854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4715701937675476},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.41692090034484863},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32396090030670166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2499294877052307},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09829151630401611},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.07381704449653625},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.06050571799278259}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1535557537","https://openalex.org/W3009674568","https://openalex.org/W3039459278","https://openalex.org/W4214717370","https://openalex.org/W4401416649","https://openalex.org/W6627932998","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6755816839","https://openalex.org/W6776867236","https://openalex.org/W6787713516","https://openalex.org/W6803403409","https://openalex.org/W6804276793","https://openalex.org/W6804563612","https://openalex.org/W6846841888","https://openalex.org/W6856740646","https://openalex.org/W6873125313"],"related_works":["https://openalex.org/W3148895720","https://openalex.org/W2393913406","https://openalex.org/W2356579025","https://openalex.org/W2359600231","https://openalex.org/W2380019117","https://openalex.org/W3138952546","https://openalex.org/W1987886368","https://openalex.org/W1660309994","https://openalex.org/W2369187583","https://openalex.org/W3197207153"],"abstract_inverted_index":{"In":[0,103],"reinforcement":[1],"learning":[2],"(RL),":[3],"exploiting":[4],"environmental":[5],"symmetries":[6,32],"can":[7],"significantly":[8],"enhance":[9],"efficiency,":[10],"robustness,":[11],"and":[12,21,27,46,77,115,120],"performance.":[13,121],"However,":[14],"ensuring":[15],"that":[16,43],"the":[17,63,66],"deep":[18],"RL":[19],"policy":[20],"value":[22,79],"networks":[23,42],"are":[24,44],"respectively":[25],"equivariant":[26,45,75,89,113],"invariant":[28,47,78],"to":[29,40,52,73],"exploit":[30],"these":[31],"is":[33],"a":[34,53,71,94,104],"substantial":[35],"challenge.":[36],"Related":[37],"works":[38],"try":[39],"design":[41],"by":[48],"construction,":[49],"limiting":[50],"them":[51],"very":[54],"restricted":[55],"library":[56],"of":[57,65],"components,":[58,85],"which":[59,86],"in":[60],"turn":[61],"hampers":[62],"expressiveness":[64],"networks.":[67],"This":[68],"paper":[69],"proposes":[70],"method":[72],"construct":[74],"policies":[76],"functions":[80],"without":[81],"specialized":[82],"neural":[83],"network":[84],"we":[87,110],"term":[88,96],"ensembles.":[90],"We":[91],"further":[92],"add":[93],"regularization":[95,116],"for":[97],"adding":[98],"inductive":[99],"bias":[100],"during":[101],"training.":[102],"map-based":[105],"path":[106],"planning":[107],"case":[108],"study,":[109],"show":[111],"how":[112],"ensembles":[114],"benefit":[117],"sample":[118],"efficiency":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}