{"id":"https://openalex.org/W4387124141","doi":"https://doi.org/10.1109/case56687.2023.10260496","title":"Safe Trajectory Sampling in Model-Based Reinforcement Learning","display_name":"Safe Trajectory Sampling in Model-Based Reinforcement Learning","publication_year":2023,"publication_date":"2023-08-26","ids":{"openalex":"https://openalex.org/W4387124141","doi":"https://doi.org/10.1109/case56687.2023.10260496"},"language":"en","primary_location":{"id":"doi:10.1109/case56687.2023.10260496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case56687.2023.10260496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 19th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://discovery.ucl.ac.uk/10180162/1/P44__Zwane_CASE_2023.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027903435","display_name":"Sicelukwanda Zwane","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sicelukwanda Zwane","raw_affiliation_strings":["University College London,UCL Centre for Artificial Intelligence,UK","UCL Centre for Artificial Intelligence, University College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London,UCL Centre for Artificial Intelligence,UK","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"UCL Centre for Artificial Intelligence, University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085134635","display_name":"Denis Hadjivelichkov","orcid":"https://orcid.org/0000-0002-8239-1492"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Denis Hadjivelichkov","raw_affiliation_strings":["University College London,UCL Centre for Artificial Intelligence,UK","UCL Centre for Artificial Intelligence, University College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London,UCL Centre for Artificial Intelligence,UK","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"UCL Centre for Artificial Intelligence, University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100546106","display_name":"Yicheng Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yicheng Luo","raw_affiliation_strings":["University College London,UCL Centre for Artificial Intelligence,UK","UCL Centre for Artificial Intelligence, University College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London,UCL Centre for Artificial Intelligence,UK","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"UCL Centre for Artificial Intelligence, University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015300584","display_name":"Yasemin Bekiroglu","orcid":"https://orcid.org/0000-0002-2597-6013"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]},{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["GB","SE"],"is_corresponding":false,"raw_author_name":"Yasemin Bekiroglu","raw_affiliation_strings":["University College London,UCL Centre for Artificial Intelligence,UK","Department of Electrical Engineering, Chalmers University of Technology, Sweden","UCL Centre for Artificial Intelligence, University College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London,UCL Centre for Artificial Intelligence,UK","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"Department of Electrical Engineering, Chalmers University of Technology, Sweden","institution_ids":["https://openalex.org/I66862912"]},{"raw_affiliation_string":"UCL Centre for Artificial Intelligence, University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048122691","display_name":"Dimitrios Kanoulas","orcid":"https://orcid.org/0000-0002-3684-1472"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dimitrios Kanoulas","raw_affiliation_strings":["University College London,UCL Centre for Artificial Intelligence,UK","UCL Centre for Artificial Intelligence, University College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London,UCL Centre for Artificial Intelligence,UK","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"UCL Centre for Artificial Intelligence, University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001763022","display_name":"Marc Peter Deisenroth","orcid":"https://orcid.org/0000-0003-1503-680X"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marc Peter Deisenroth","raw_affiliation_strings":["University College London,UCL Centre for Artificial Intelligence,UK","UCL Centre for Artificial Intelligence, University College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London,UCL Centre for Artificial Intelligence,UK","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"UCL Centre for Artificial Intelligence, University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4356,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59794377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.992900013923645,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9818999767303467,"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":0.8489043712615967},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7274359464645386},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7243192791938782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6493771076202393},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6180771589279175},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5986722111701965},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5772168040275574},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5681092739105225},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5564332604408264},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5475170016288757},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.49033522605895996},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.39502206444740295},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14812549948692322}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8489043712615967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7274359464645386},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7243192791938782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6493771076202393},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6180771589279175},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5986722111701965},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5772168040275574},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5681092739105225},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5564332604408264},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5475170016288757},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.49033522605895996},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.39502206444740295},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14812549948692322},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/case56687.2023.10260496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case56687.2023.10260496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 19th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10180162","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10180162/","pdf_url":"https://discovery.ucl.ac.uk/10180162/1/P44__Zwane_CASE_2023.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: IEEE International Conference on Automation Science and Engineering. IEEE: Auckland, New Zealand. (2023)","raw_type":"Proceedings paper"},{"id":"pmh:oai:research.chalmers.se:538099","is_oa":false,"landing_page_url":"https://research.chalmers.se/en/publication/538099","pdf_url":null,"source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null}],"best_oa_location":{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10180162","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10180162/","pdf_url":"https://discovery.ucl.ac.uk/10180162/1/P44__Zwane_CASE_2023.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: IEEE International Conference on Automation Science and Engineering. IEEE: Auckland, New Zealand. (2023)","raw_type":"Proceedings paper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4583412171","display_name":"UKRI AI Centre for Doctoral Training in Foundational Artificial Intelligence","funder_award_id":"EP/S021566/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387124141.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W1971086298","https://openalex.org/W1977655452","https://openalex.org/W2018705428","https://openalex.org/W2037333043","https://openalex.org/W2108734173","https://openalex.org/W2139769245","https://openalex.org/W2140135625","https://openalex.org/W2161819990","https://openalex.org/W2408670836","https://openalex.org/W2412669390","https://openalex.org/W2575705757","https://openalex.org/W2580909119","https://openalex.org/W2700407638","https://openalex.org/W2762483932","https://openalex.org/W2785389871","https://openalex.org/W3161095009","https://openalex.org/W4205513846","https://openalex.org/W4211049957","https://openalex.org/W4287603018","https://openalex.org/W4287816721","https://openalex.org/W4298206671","https://openalex.org/W6605566567","https://openalex.org/W6676172287","https://openalex.org/W6680657880","https://openalex.org/W6680880767","https://openalex.org/W6713989974","https://openalex.org/W6740033195","https://openalex.org/W6748519856","https://openalex.org/W6751494529","https://openalex.org/W6786335862"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W1941703695","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W3131574667","https://openalex.org/W1964286703","https://openalex.org/W2169866437"],"abstract_inverted_index":{"Model-based":[0],"reinforcement":[1,77,111],"learning":[2,31,78,112],"aims":[3],"to":[4,8,45,55,67],"learn":[5],"a":[6,10,15,58,99,109,158],"policy":[7,30,50],"solve":[9],"target":[11],"task":[12],"by":[13],"leveraging":[14],"learned":[16,92],"dynamics":[17,81,93],"model.":[18],"This":[19],"approach,":[20],"paired":[21],"with":[22,79,143],"principled":[23],"handling":[24],"of":[25,75],"uncertainty":[26],"allows":[27],"for":[28],"data-efficient":[29],"in":[32,72],"robotics.":[33],"However,":[34],"the":[35,49,69,73,91,129,135],"physical":[36],"environment":[37],"has":[38],"feasibility":[39],"and":[40,146],"safety":[41,105,118,163],"constraints":[42,71,119],"that":[43],"need":[44],"be":[46,96,154],"incorporated":[47],"into":[48,122],"before":[51],"it":[52],"is":[53],"safe":[54,150],"execute":[56],"on":[57,98,128,138,157],"real":[59,100,159],"robot.":[60],"In":[61,83],"this":[62],"work,":[63],"we":[64,85],"study":[65],"how":[66,87,148],"enforce":[68],"aforementioned":[70],"context":[74],"model-based":[76,110],"probabilistic":[80],"models.":[82],"particular,":[84],"investigate":[86],"trajectories":[88],"sampled":[89],"from":[90],"model":[94],"can":[95,153],"used":[97,156],"robot,":[101],"while":[102],"fulfilling":[103],"user-specified":[104],"requirements.":[106],"We":[107,133],"present":[108],"approach":[113,137,152],"using":[114],"Gaussian":[115,126],"processes":[116],"where":[117],"are":[120],"taken":[121],"account":[123],"without":[124,161],"simplifying":[125],"assumptions":[127],"predictive":[130],"state":[131],"distributions.":[132],"evaluate":[134],"proposed":[136],"different":[139],"continuous":[140],"control":[141],"tasks":[142],"varying":[144],"complexity":[145],"demonstrate":[147],"our":[149],"trajectory-sampling":[151],"directly":[155],"robot":[160],"violating":[162],"constraints.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}