{"id":"https://openalex.org/W4403918195","doi":"https://doi.org/10.1109/lra.2024.3488402","title":"Safe Reinforcement Learning of Robot Trajectories in the Presence of Moving Obstacles","display_name":"Safe Reinforcement Learning of Robot Trajectories in the Presence of Moving Obstacles","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4403918195","doi":"https://doi.org/10.1109/lra.2024.3488402"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3488402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3488402","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5003356244","display_name":"Jonas C. Kiemel","orcid":"https://orcid.org/0000-0001-8044-5111"},"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":"Jonas Kiemel","raw_affiliation_strings":["Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology (KIT), Germany"],"raw_orcid":"https://orcid.org/0000-0001-8044-5111","affiliations":[{"raw_affiliation_string":"Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology (KIT), Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026007843","display_name":"Ludovic Righetti","orcid":"https://orcid.org/0000-0002-6458-9112"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ludovic Righetti","raw_affiliation_strings":["Tandon School of Engineering, New York University (NYU), Brooklyn, USA","Tandon School of Engineering, New York University (NYU), USA"],"raw_orcid":"https://orcid.org/0000-0002-6458-9112","affiliations":[{"raw_affiliation_string":"Tandon School of Engineering, New York University (NYU), Brooklyn, USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Tandon School of Engineering, New York University (NYU), USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018921223","display_name":"Torsten Kr\u00f6ger","orcid":null},"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":"Torsten Kr\u00f6ger","raw_affiliation_strings":["Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology (KIT), Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology (KIT), Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012730104","display_name":"Tamim Asfour","orcid":"https://orcid.org/0000-0003-4879-7680"},"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":"Tamim Asfour","raw_affiliation_strings":["Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology (KIT), Germany"],"raw_orcid":"https://orcid.org/0000-0003-4879-7680","affiliations":[{"raw_affiliation_string":"Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology (KIT), Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1114,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81798788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"9","issue":"12","first_page":"11353","last_page":"11360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8458999991416931,"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":0.8458999991416931,"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":0.8215000033378601,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.8172000050544739,"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":0.8044383525848389},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6297388076782227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5765447616577148},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5344055891036987},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.525102972984314},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4263290762901306},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.2682018280029297},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2055303156375885},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.0650542676448822}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8044383525848389},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6297388076782227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5765447616577148},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5344055891036987},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.525102972984314},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4263290762901306},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2682018280029297},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2055303156375885},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0650542676448822}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3488402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3488402","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2037333043","https://openalex.org/W2104906962","https://openalex.org/W2141698884","https://openalex.org/W2892521964","https://openalex.org/W2963293747","https://openalex.org/W2963525569","https://openalex.org/W2966735560","https://openalex.org/W2998619042","https://openalex.org/W3135269237","https://openalex.org/W3142005321","https://openalex.org/W3150718622","https://openalex.org/W3195968524","https://openalex.org/W3207398607","https://openalex.org/W4206497039","https://openalex.org/W4313196885","https://openalex.org/W4386432124","https://openalex.org/W6600644339","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6741002519","https://openalex.org/W6784630725","https://openalex.org/W6800776581"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W2171010636"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,22,151,204],"present":[4],"an":[5,63,142],"approach":[6,175,208],"for":[7,43,102,176],"learning":[8,41],"collision-free":[9],"robot":[10,34,90],"trajectories":[11,212],"in":[12,113,124,213],"the":[13,46,54,67,85,89,104,114,121,135,163,171],"presence":[14],"of":[15,57,88,106,145,165,173],"moving":[16],"obstacles.":[17],"As":[18],"a":[19,24,58,107,128,154,158,182,186,201],"first":[20],"step,":[21],"train":[23],"backup":[25,47],"policy":[26,48],"to":[27,52,61],"generate":[28,210],"evasive":[29],"movements":[30],"from":[31],"arbitrary":[32],"initial":[33],"states":[35],"using":[36],"model-free":[37],"reinforcement":[38],"learning.":[39],"When":[40],"policies":[42],"other":[44],"tasks,":[45],"can":[49,192,209],"be":[50,193],"used":[51,133],"estimate":[53],"potential":[55],"risk":[56,69,105,130,164],"collision":[59],"and":[60,97,157,178,185],"offer":[62],"alternative":[64],"action":[65,77,81],"if":[66],"estimated":[68],"is":[70,78,116,132,138,147],"considered":[71,194],"too":[72],"high.":[73],"No":[74],"matter":[75],"which":[76],"selected,":[79],"our":[80,174,207],"space":[82],"ensures":[83],"that":[84,206],"kinematic":[86],"limits":[87],"joints":[91],"are":[92],"not":[93],"violated.":[94],"We":[95],"analyze":[96],"evaluate":[98],"two":[99],"different":[100],"methods":[101],"estimating":[103],"collision.":[108],"A":[109],"physics":[110],"simulation":[111],"performed":[112],"background":[115],"computationally":[117],"expensive":[118],"but":[119,141],"provides":[120],"best":[122],"results":[123,169],"deterministic":[125,177],"environments.":[126],"If":[127],"data-based":[129],"estimator":[131],"instead,":[134],"computational":[136],"effort":[137],"significantly":[139],"reduced,":[140],"additional":[143],"source":[144],"error":[146],"introduced.":[148],"For":[149],"evaluation,":[150],"successfully":[152],"learn":[153],"reaching":[155],"task":[156,160],"basketball":[159],"while":[161],"keeping":[162],"collisions":[166],"low.":[167],"The":[168],"demonstrate":[170],"effectiveness":[172],"stochastic":[179],"environments,":[180],"including":[181],"human-robot":[183],"scenario":[184],"ball":[187],"environment,":[188],"where":[189],"no":[190],"state":[191],"permanently":[195],"safe.":[196],"By":[197],"conducting":[198],"experiments":[199],"with":[200],"real":[202,214],"robot,":[203],"show":[205],"safe":[211],"time.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}