{"id":"https://openalex.org/W4416749552","doi":"https://doi.org/10.1109/iros60139.2025.11247602","title":"Learning Manipulation Skills through Robot Chain-of-Thought with Sparse Failure Guidance","display_name":"Learning Manipulation Skills through Robot Chain-of-Thought with Sparse Failure Guidance","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749552","doi":"https://doi.org/10.1109/iros60139.2025.11247602"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247602","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/A5101432659","display_name":"Kaifeng Zhang","orcid":"https://orcid.org/0000-0002-8659-1619"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaifeng Zhang","raw_affiliation_strings":["Shanghai Qi Zhi Institute"],"affiliations":[{"raw_affiliation_string":"Shanghai Qi Zhi Institute","institution_ids":["https://openalex.org/I4210122302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094077398","display_name":"Zhao-Heng Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao-Heng Yin","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090931883","display_name":"Weirui Ye","orcid":"https://orcid.org/0009-0000-9557-4506"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weirui Ye","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102873084","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0003-0348-2546"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101432659"],"corresponding_institution_ids":["https://openalex.org/I4210122302"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20556854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8012","last_page":"8018"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4771000146865845,"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":0.4771000146865845,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.15780000388622284,"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":0.1370999962091446,"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/process","display_name":"Process (computing)","score":0.6758999824523926},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6118000149726868},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.46219998598098755},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.375},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.3734000027179718},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.36059999465942383},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.328900009393692},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.32710000872612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6941999793052673},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6758999824523926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6165000200271606},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6118000149726868},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44369998574256897},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.375},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.36059999465942383},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.32710000872612},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247602","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2498525044","https://openalex.org/W2604382266","https://openalex.org/W2769112066","https://openalex.org/W2883429621","https://openalex.org/W3091471537","https://openalex.org/W3203711169","https://openalex.org/W4385403858","https://openalex.org/W4385430679","https://openalex.org/W4402354083"],"related_works":[],"abstract_inverted_index":{"Reward":[0],"engineering":[1],"for":[2,27],"policy":[3],"learning":[4,46,86],"has":[5],"been":[6],"a":[7,82,111,124],"long-standing":[8],"challenge":[9],"in":[10,24],"robotics.":[11],"Recently,":[12],"to":[13,44,71,88,118],"avoid":[14],"manual":[15],"reward":[16,37,59,75],"designs,":[17],"vision-language":[18],"models":[19],"(VLMs)":[20],"have":[21],"shown":[22],"promise":[23],"defining":[25],"rewards":[26],"teaching":[28],"robots":[29],"manipulation":[30,127],"skills.":[31],"However,":[32],"existing":[33],"work":[34],"often":[35],"provides":[36],"guidance":[38,76],"that":[39,95],"is":[40],"too":[41],"coarse,":[42],"leading":[43],"insufficient":[45],"processes.":[47],"In":[48],"this":[49,53,69],"paper,":[50],"we":[51,62],"address":[52],"issue":[54],"by":[55],"implementing":[56],"more":[57,73],"fine-grained":[58],"guidance.":[60],"Specifically,":[61,107],"decompose":[63],"tasks":[64],"into":[65],"simpler":[66],"sub-tasks,":[67],"using":[68],"decomposition":[70],"offer":[72],"informative":[74],"with":[77],"VLMs.":[78],"We":[79],"also":[80],"propose":[81],"VLM-based":[83],"self":[84],"imitation":[85],"process":[87],"speed":[89],"up":[90],"learning.":[91],"Empirical":[92],"evidence":[93],"demonstrates":[94],"our":[96,108],"algorithm":[97,109],"consistently":[98],"outperforms":[99],"baselines":[100],"such":[101],"as":[102],"CLIP,":[103],"LIV,":[104],"and":[105],"RoboCLIP.":[106],"achieves":[110],"5:4":[112],"higher":[113],"average":[114],"success":[115],"rates":[116],"compared":[117],"the":[119],"best":[120],"baseline,":[121],"RoboCLIP,":[122],"across":[123],"series":[125],"of":[126],"tasks.":[128]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}