{"id":"https://openalex.org/W4405785981","doi":"https://doi.org/10.1109/iros58592.2024.10801366","title":"Reinforcement Learning for Active Search and Grasp in Clutter","display_name":"Reinforcement Learning for Active Search and Grasp in Clutter","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785981","doi":"https://doi.org/10.1109/iros58592.2024.10801366"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801366","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":null,"display_name":"Thomas Pitcher","orcid":null},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Thomas Pitcher","raw_affiliation_strings":["The University of Queensland,School of Electrical Engineering and Computer Science,Brisbane,Australia,4072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland,School of Electrical Engineering and Computer Science,Brisbane,Australia,4072","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065770056","display_name":"Julian F\u00f6rster","orcid":"https://orcid.org/0000-0002-1163-1065"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julian F\u00f6rster","raw_affiliation_strings":["ETH Zürich,Autonomous Systems Lab,Zürich,Switzerland,8092"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zürich,Autonomous Systems Lab,Zürich,Switzerland,8092","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009492797","display_name":"Jen Jen Chung","orcid":"https://orcid.org/0000-0001-7828-0741"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jen Jen Chung","raw_affiliation_strings":["The University of Queensland,School of Electrical Engineering and Computer Science,Brisbane,Australia,4072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland,School of Electrical Engineering and Computer Science,Brisbane,Australia,4072","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20718142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7301","last_page":"7306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9916999936103821,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9916999936103821,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9625999927520752,"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":0.9175999760627747,"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/grasp","display_name":"GRASP","score":0.8574891090393066},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.809531569480896},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.7570593357086182},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7141807079315186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4733574390411377},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.45214730501174927},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.4349440634250641},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34018397331237793},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16431009769439697},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.09356293082237244}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.8574891090393066},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.809531569480896},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.7570593357086182},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7141807079315186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4733574390411377},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.45214730501174927},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4349440634250641},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34018397331237793},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16431009769439697},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.09356293082237244},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801366","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1980076217","https://openalex.org/W2046796791","https://openalex.org/W2126496149","https://openalex.org/W2157692698","https://openalex.org/W2600030077","https://openalex.org/W2769883686","https://openalex.org/W2908549092","https://openalex.org/W2914358862","https://openalex.org/W2918333121","https://openalex.org/W3004047800","https://openalex.org/W3090299930","https://openalex.org/W3090679498","https://openalex.org/W3092037789","https://openalex.org/W3130791072","https://openalex.org/W3206772186","https://openalex.org/W4205892839","https://openalex.org/W4285102453","https://openalex.org/W4312333838","https://openalex.org/W4323527514"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W2326995835","https://openalex.org/W165915117","https://openalex.org/W2059402478","https://openalex.org/W2123347777","https://openalex.org/W4387804363","https://openalex.org/W2019547100","https://openalex.org/W2477150073","https://openalex.org/W2515493494"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"Active":[4],"Search":[5],"policy":[6],"that":[7],"balances":[8],"between":[9],"moving":[10],"the":[11,53,57,60,72,78,85],"camera":[12],"and":[13,20,45,66,83,94,106],"removing":[14],"occluding":[15],"objects":[16],"to":[17,70,110],"search":[18],"for":[19],"retrieve":[21],"a":[22,37,98],"target":[23,61,86],"object":[24,62,87],"in":[25,42,56,88,92,101],"clutter.":[26],"While":[27],"both":[28,102],"types":[29],"of":[30,36,74,81],"action":[31,76],"can":[32],"reveal":[33],"unobserved":[34],"parts":[35],"scene,":[38],"they":[39],"typically":[40],"vary":[41],"execution":[43,104],"complexity":[44],"time.":[46,90],"Our":[47],"proposed":[48],"method":[49],"explicitly":[50],"reasons":[51],"about":[52],"occluded":[54],"spaces":[55],"scene":[58],"where":[59],"may":[63],"be":[64],"hidden,":[65],"uses":[67],"reinforcement":[68],"learning":[69],"compute":[71],"value":[73],"each":[75],"with":[77],"ultimate":[79],"goal":[80],"finding":[82],"retrieving":[84],"minimal":[89],"Results":[91],"simulation":[93],"real-world":[95],"experiments":[96],"demonstrate":[97],"significant":[99],"improvement":[100],"task":[103],"speed":[105],"success":[107],"rate":[108],"compared":[109],"baseline":[111],"grasping":[112],"strategies.":[113]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}