{"id":"https://openalex.org/W4401417060","doi":"https://doi.org/10.1109/icra57147.2024.10611483","title":"Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks","display_name":"Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401417060","doi":"https://doi.org/10.1109/icra57147.2024.10611483"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611483","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/A5068734838","display_name":"Eleftherios Triantafyllidis","orcid":"https://orcid.org/0000-0001-7578-4290"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eleftherios Triantafyllidis","raw_affiliation_strings":["The University of Edinburgh,School of Informatics,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Edinburgh,School of Informatics,United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047256432","display_name":"Filippos Christianos","orcid":"https://orcid.org/0000-0002-4230-2846"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Filippos Christianos","raw_affiliation_strings":["The University of Edinburgh,School of Informatics,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Edinburgh,School of Informatics,United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351560","display_name":"Zhibin Li","orcid":"https://orcid.org/0000-0002-6357-7419"},"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":"Zhibin Li","raw_affiliation_strings":["University College London,Department of Computer Science,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London,Department of Computer Science,United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3304,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.88541693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7493","last_page":"7500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6448414921760559},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.6089247465133667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.517924964427948},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38497740030288696},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3309163749217987},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17948070168495178},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11591193079948425}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6448414921760559},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.6089247465133667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.517924964427948},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38497740030288696},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3309163749217987},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17948070168495178},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11591193079948425},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611483","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1970890515","https://openalex.org/W2101524054","https://openalex.org/W2139612737","https://openalex.org/W2462906003","https://openalex.org/W2559655401","https://openalex.org/W2605102758","https://openalex.org/W2612972698","https://openalex.org/W2736601468","https://openalex.org/W2747329762","https://openalex.org/W2798357025","https://openalex.org/W2889987506","https://openalex.org/W2912083425","https://openalex.org/W2919115771","https://openalex.org/W2962787969","https://openalex.org/W2963276097","https://openalex.org/W2963669336","https://openalex.org/W2968095426","https://openalex.org/W2973266032","https://openalex.org/W3100035092","https://openalex.org/W3111294788","https://openalex.org/W3166396011","https://openalex.org/W3184808923","https://openalex.org/W3185691815","https://openalex.org/W4212774754","https://openalex.org/W4221143046","https://openalex.org/W4224912544","https://openalex.org/W4283266503","https://openalex.org/W4287071861","https://openalex.org/W4319453286","https://openalex.org/W4320342509","https://openalex.org/W4321011670","https://openalex.org/W4322825501","https://openalex.org/W4380993732","https://openalex.org/W4386499064","https://openalex.org/W4401417060","https://openalex.org/W6684921986","https://openalex.org/W6717230150","https://openalex.org/W6718092244","https://openalex.org/W6718836005","https://openalex.org/W6735033012","https://openalex.org/W6738087714","https://openalex.org/W6738741286","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6753526802","https://openalex.org/W6756303580","https://openalex.org/W6763775148","https://openalex.org/W6765008394","https://openalex.org/W6766900654","https://openalex.org/W6771418060","https://openalex.org/W6775686901","https://openalex.org/W6778883912","https://openalex.org/W6788860121","https://openalex.org/W6791353385","https://openalex.org/W6803891570","https://openalex.org/W6809646742","https://openalex.org/W6810640255","https://openalex.org/W6849548236","https://openalex.org/W6849843017","https://openalex.org/W6849861922","https://openalex.org/W6849895545","https://openalex.org/W6853664340"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Current":[0],"reinforcement":[1,51],"learning":[2,52,70,117],"algorithms":[3],"struggle":[4],"in":[5,12,50,72,108],"sparse":[6,58],"and":[7,67,78,88,102,114,131,140],"complex":[8,80],"environments,":[9],"most":[10],"notably":[11,95],"long-horizon":[13,56],"manipulation":[14,61,82],"tasks":[15],"entailing":[16],"a":[17,79],"plethora":[18],"of":[19,106,138],"different":[20,127],"sequences.":[21],"In":[22],"this":[23],"work,":[24],"we":[25],"propose":[26],"the":[27,47,103],"Intrinsically":[28],"Guided":[29],"Exploration":[30],"from":[31],"Large":[32],"Language":[33],"Models":[34],"(IGE-LLMs)":[35],"framework.":[36],"By":[37],"leveraging":[38],"LLMs":[39,107],"as":[40],"an":[41,73],"assistive":[42],"intrinsic":[43,69,100,128],"reward,":[44],"IGE-LLMs":[45,92],"guides":[46],"exploratory":[48],"process":[49],"to":[53,126],"address":[54],"intricate":[55],"with":[57,76],"rewards":[59],"robotic":[60,81],"tasks.":[62],"We":[63],"evaluate":[64],"our":[65],"framework":[66],"related":[68,99],"methods":[71,101,118],"environment":[74],"challenged":[75,84],"exploration,":[77],"task":[83],"by":[85],"both":[86],"exploration":[87],"long-horizons.":[89],"Results":[90],"show":[91],"(i)":[93],"exhibit":[94],"higher":[96],"performance":[97],"over":[98],"direct":[104],"use":[105],"decision-making,":[109],"(ii)":[110],"can":[111],"be":[112],"combined":[113],"complement":[115],"existing":[116],"highlighting":[119],"its":[120],"modularity,":[121],"(iii)":[122],"are":[123],"fairly":[124],"insensitive":[125],"scaling":[129],"parameters,":[130],"(iv)":[132],"maintain":[133],"robustness":[134],"against":[135],"increased":[136],"levels":[137],"uncertainty":[139],"horizons.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}