{"id":"https://openalex.org/W4401415460","doi":"https://doi.org/10.1109/icra57147.2024.10610047","title":"Reinforcement Learning in a Safety-Embedded MDP with Trajectory Optimization","display_name":"Reinforcement Learning in a Safety-Embedded MDP with Trajectory Optimization","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401415460","doi":"https://doi.org/10.1109/icra57147.2024.10610047"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5101993133","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0001-8768-9450"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA,15213"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080937886","display_name":"Wenxuan Zhou","orcid":"https://orcid.org/0000-0003-1199-885X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenxuan Zhou","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA,15213"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037613999","display_name":"Zuxin Liu","orcid":"https://orcid.org/0000-0001-7412-5074"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zuxin Liu","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA,15213"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037644321","display_name":"Ding Zhao","orcid":"https://orcid.org/0000-0002-9400-8446"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ding Zhao","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA,15213"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037048516","display_name":"David Held","orcid":"https://orcid.org/0000-0003-0537-1508"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Held","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA,15213"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101993133"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.5499,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64939454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2845","last_page":"2851"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998000264167786,"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":0.9998000264167786,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9972000122070312,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9969000220298767,"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":0.7989663481712341},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7023823261260986},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6663267612457275},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5314031839370728},{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"Trajectory optimization","score":0.5228074789047241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44661420583724976},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3420313596725464},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16122928261756897},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.078518807888031}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7989663481712341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7023823261260986},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6663267612457275},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5314031839370728},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.5228074789047241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44661420583724976},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3420313596725464},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16122928261756897},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.078518807888031},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W2002440441","https://openalex.org/W2155007355","https://openalex.org/W2158782408","https://openalex.org/W2161076907","https://openalex.org/W2295255295","https://openalex.org/W2736506089","https://openalex.org/W2736887377","https://openalex.org/W2784465508","https://openalex.org/W2889731659","https://openalex.org/W2892521964","https://openalex.org/W2900747027","https://openalex.org/W2911618937","https://openalex.org/W2963293747","https://openalex.org/W2963575966","https://openalex.org/W2981030070","https://openalex.org/W2990747716","https://openalex.org/W2994712737","https://openalex.org/W3089422924","https://openalex.org/W3101517963","https://openalex.org/W3102334304","https://openalex.org/W3127561923","https://openalex.org/W3200871490","https://openalex.org/W3206530605","https://openalex.org/W4206497039","https://openalex.org/W4212769423","https://openalex.org/W4221144242","https://openalex.org/W4226116356","https://openalex.org/W4286224728","https://openalex.org/W4287726322","https://openalex.org/W4293775970","https://openalex.org/W4294555834","https://openalex.org/W4294562617","https://openalex.org/W4298857966","https://openalex.org/W4306705058","https://openalex.org/W4323527626","https://openalex.org/W6637967152","https://openalex.org/W6682849425","https://openalex.org/W6683620479","https://openalex.org/W6714477741","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6747473740","https://openalex.org/W6747790125","https://openalex.org/W6751535212","https://openalex.org/W6754302822","https://openalex.org/W6756547993","https://openalex.org/W6759111761","https://openalex.org/W6771280675","https://openalex.org/W6785471904","https://openalex.org/W6796690604","https://openalex.org/W6803282296","https://openalex.org/W6809864479","https://openalex.org/W6810667139","https://openalex.org/W6810739325","https://openalex.org/W6838325272","https://openalex.org/W6840335140","https://openalex.org/W6846122673"],"related_works":["https://openalex.org/W4385832323","https://openalex.org/W4244391535","https://openalex.org/W2356996864","https://openalex.org/W2904060783","https://openalex.org/W2015393961","https://openalex.org/W2378339670","https://openalex.org/W2359353485","https://openalex.org/W2139910871","https://openalex.org/W2361427670","https://openalex.org/W2119925415"],"abstract_inverted_index":{"Safe":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"plays":[4],"an":[5],"important":[6],"role":[7],"in":[8,90,120],"applying":[9],"RL":[10,35,61],"algorithms":[11],"to":[12,24,39],"safety-critical":[13],"real-world":[14,110],"applications,":[15],"addressing":[16],"the":[17,50,134],"trade-off":[18,42],"between":[19],"maximizing":[20],"rewards":[21,101],"and":[22,82,102,117,136],"adhering":[23],"safety":[25,47,81,104],"constraints.":[26],"This":[27,86],"work":[28],"introduces":[29],"a":[30,54,64,75,115,121],"novel":[31,87],"approach":[32,45,88],"that":[33,68],"combines":[34],"with":[36],"trajectory":[37,76],"optimization":[38],"manage":[40],"this":[41],"effectively.":[43],"Our":[44],"embeds":[46],"constraints":[48],"within":[49],"action":[51],"space":[52],"of":[53,66,125],"modified":[55],"Markov":[56],"Decision":[57],"Process":[58],"(MDP).":[59],"The":[60,108],"agent":[62],"produces":[63],"sequence":[65],"actions":[67],"are":[69,131],"transformed":[70],"into":[71],"safe":[72,116],"trajectories":[73],"by":[74],"optimizer,":[77],"thereby":[78],"effectively":[79],"ensuring":[80],"increasing":[83],"training":[84],"stability.":[85],"excels":[89],"its":[91],"performance":[92],"on":[93,138],"challenging":[94],"Safety":[95],"Gym":[96],"tasks,":[97],"achieving":[98],"significantly":[99],"higher":[100],"near-zero":[103],"violations":[105],"during":[106],"inference.":[107],"method\u2019s":[109],"applicability":[111],"is":[112],"demonstrated":[113],"through":[114],"effective":[118],"deployment":[119],"real":[122],"robot":[123],"task":[124],"box-pushing":[126],"around":[127],"obstacles.":[128],"Further":[129],"insights":[130],"available":[132],"from":[133],"videos":[135],"appendix":[137],"our":[139],"website:":[140],"https://sites.google.com/view/safemdp.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}