{"id":"https://openalex.org/W4416749730","doi":"https://doi.org/10.1109/iros60139.2025.11245841","title":"SIME: Enhancing Policy Self-Improvement with Modal-level Exploration","display_name":"SIME: Enhancing Policy Self-Improvement with Modal-level Exploration","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749730","doi":"https://doi.org/10.1109/iros60139.2025.11245841"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11245841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":"https://openalex.org/A5019869909","display_name":"Yang Jin","orcid":"https://orcid.org/0009-0000-7353-9849"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Jin","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100308848","display_name":"Jun Lv","orcid":"https://orcid.org/0000-0003-4328-0420"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Lv","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119825204","display_name":"Wenye Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenye Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongjie Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjie Fang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031174631","display_name":"Yong\u2013Lu Li","orcid":"https://orcid.org/0000-0003-0478-0692"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong-Lu Li","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010726528","display_name":"Cewu Lu","orcid":"https://orcid.org/0000-0002-4023-9257"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cewu Lu","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18560535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9792","last_page":"9799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7742000222206116,"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":0.7742000222206116,"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":0.06289999932050705,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.03539999946951866,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6294999718666077},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6288999915122986},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5629000067710876},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4510999917984009},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4392000138759613},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3407999873161316}],"concepts":[{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6294999718666077},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6288999915122986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6107000112533569},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5629000067710876},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4578999876976013},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3407999873161316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32899999618530273},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.3084000051021576},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2808000147342682},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2728999853134155},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11245841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":18,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2951360122","https://openalex.org/W2973229164","https://openalex.org/W4385430582","https://openalex.org/W4385430674","https://openalex.org/W4390874575","https://openalex.org/W4401415042","https://openalex.org/W4401415287","https://openalex.org/W4401416214","https://openalex.org/W4402354047","https://openalex.org/W4402354127","https://openalex.org/W4403129459","https://openalex.org/W4403337227","https://openalex.org/W4403670026","https://openalex.org/W4405785353","https://openalex.org/W4413362511","https://openalex.org/W4413918191","https://openalex.org/W4413947030"],"related_works":[],"abstract_inverted_index":{"Self-improvement":[0],"requires":[1],"robotic":[2,136],"systems":[3],"to":[4,24,43,52,66,130],"initially":[5],"learn":[6],"from":[7,105],"human-provided":[8],"data":[9,56,72],"and":[10,71,89,102,120,134,145],"then":[11],"gradually":[12],"enhance":[13],"their":[14,28,45],"capabilities":[15],"through":[16,30],"interaction":[17],"with":[18],"the":[19,64,83,93,98],"environment.":[20],"This":[21],"is":[22,37],"similar":[23],"how":[25],"humans":[26],"improve":[27],"skills":[29],"continuous":[31],"practice.":[32],"However,":[33],"achieving":[34],"effective":[35,113],"self-improvement":[36,115,126],"challenging,":[38],"primarily":[39],"because":[40],"robots":[41],"tend":[42],"repeat":[44],"existing":[46],"abilities":[47],"during":[48,80],"interactions,":[49],"often":[50],"failing":[51],"generate":[53],"new,":[54],"valuable":[55,100],"for":[57,108,125],"learning.":[58,109],"In":[59],"this":[60],"paper,":[61],"we":[62,96],"identify":[63],"key":[65],"successful":[67],"self-improvement:":[68],"modal-level":[69,77],"exploration":[70,78],"selection.":[73],"By":[74],"incorporating":[75],"a":[76,140],"mechanism":[79],"policy":[81],"execution,":[82],"robot":[84,114],"can":[85],"produce":[86],"more":[87,132],"diverse":[88],"multi-modal":[90],"interactions.":[91],"At":[92],"same":[94],"time,":[95],"select":[97],"most":[99],"trials":[101],"high-quality":[103],"segments":[104],"these":[106],"interactions":[107],"We":[110],"successfully":[111],"demonstrate":[112],"on":[116],"both":[117],"simulation":[118],"benchmarks":[119],"real-world":[121],"experiments.":[122],"The":[123],"capability":[124],"will":[127],"enable":[128],"us":[129],"develop":[131],"robust":[133],"high-success-rate":[135],"control":[137],"strategies":[138],"at":[139,150],"lower":[141],"cost.":[142],"Our":[143],"code":[144],"experiment":[146],"scripts":[147],"are":[148],"available":[149],"ericjin2002.github.io/SIME.":[151]},"counts_by_year":[],"updated_date":null,"created_date":"2025-11-28T00:00:00"}