{"id":"https://openalex.org/W7128475296","doi":"https://doi.org/10.15607/rss.2026.xxii.064","title":"Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning","display_name":"Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning","publication_year":2026,"publication_date":"2026-07-13","ids":{"openalex":"https://openalex.org/W7128475296","doi":"https://doi.org/10.15607/rss.2026.xxii.064"},"language":"en","primary_location":{"id":"doi:10.15607/rss.2026.xxii.064","doi":"https://doi.org/10.15607/rss.2026.xxii.064","is_oa":true,"landing_page_url":"https://doi.org/10.15607/rss.2026.xxii.064","pdf_url":"https://doi.org/10.15607/rss.2026.xxii.064","source":{"id":"https://openalex.org/S4306420803","display_name":"Robotics: Science and Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics: Science and Systems XXII","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.15607/rss.2026.xxii.064","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031297903","display_name":"Milan Ganai","orcid":"https://orcid.org/0009-0001-1825-3650","observed_orcids":["https://orcid.org/0009-0001-1825-3650"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Milan Ganai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110725449","display_name":"Katie Z Luo","orcid":"https://orcid.org/0009-0008-5797-534X","observed_orcids":["https://orcid.org/0009-0008-5797-534X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katie Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090942799","display_name":"Jonas Frey","orcid":"https://orcid.org/0000-0002-7401-2173","observed_orcids":["https://orcid.org/0000-0002-7401-2173"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonas Frey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026961968","display_name":"Clark Barrett","orcid":"https://orcid.org/0000-0002-9522-3084","observed_orcids":["https://orcid.org/0000-0002-9522-3084"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Clark Barrett","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050003000","display_name":"Marco Pavone","orcid":"https://orcid.org/0000-0002-0206-4337","observed_orcids":["https://orcid.org/0000-0002-0206-4337"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Pavone","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.5584,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.96810786,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.6366999745368958,"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":0.6366999745368958,"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":0.3118000030517578,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.022600000724196434,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-reasoning","display_name":"embodied reasoning","score":0.8199999928474426},{"id":"https://openalex.org/keywords/chain-of-thought-reasoning","display_name":"chain-of-thought reasoning","score":0.8320000171661377},{"id":"https://openalex.org/keywords/reasoning-distillation","display_name":"reasoning distillation","score":0.4659999907016754},{"id":"https://openalex.org/keywords/vision-language-action-models","display_name":"vision-language-action models","score":0.8240000009536743},{"id":"https://openalex.org/keywords/action-prediction","display_name":"action prediction","score":0.7429999709129333},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.8090000152587891},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.9819999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7709000110626221},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.704800009727478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6391000151634216},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.6172000169754028},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5776000022888184},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.564300000667572},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4027000069618225},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.40130001306533813},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.3813000023365021},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3743000030517578},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.31049999594688416},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.29989999532699585},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C107848011","wikidata":"https://www.wikidata.org/wiki/Q4680756","display_name":"Adaptive reasoning","level":4,"score":0.2549999952316284},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.15607/rss.2026.xxii.064","doi":"https://doi.org/10.15607/rss.2026.xxii.064","is_oa":true,"landing_page_url":"https://doi.org/10.15607/rss.2026.xxii.064","pdf_url":"https://doi.org/10.15607/rss.2026.xxii.064","source":{"id":"https://openalex.org/S4306420803","display_name":"Robotics: Science and Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics: Science and Systems XXII","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2602.08167","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.08167","pdf_url":"https://arxiv.org/pdf/2602.08167","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.08167","doi":"https://doi.org/10.48550/arxiv.2602.08167","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.08167","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.15607/rss.2026.xxii.064","doi":"https://doi.org/10.15607/rss.2026.xxii.064","is_oa":true,"landing_page_url":"https://doi.org/10.15607/rss.2026.xxii.064","pdf_url":"https://doi.org/10.15607/rss.2026.xxii.064","source":{"id":"https://openalex.org/S4306420803","display_name":"Robotics: Science and Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics: Science and Systems XXII","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3612158132","display_name":"Category I: Anvil - A National Composable Advanced Computational Resource for the Future of Science and Engineering","funder_award_id":"2005632","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"},{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128475296.pdf","grobid_xml":"https://content.openalex.org/works/W7128475296.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W2605576515","https://openalex.org/W2902907165","https://openalex.org/W3195577433","https://openalex.org/W4318751977","https://openalex.org/W4367000491","https://openalex.org/W4380993527","https://openalex.org/W4382603221","https://openalex.org/W4383109478","https://openalex.org/W4384918448","https://openalex.org/W4385430674","https://openalex.org/W4385430679","https://openalex.org/W4386655575","https://openalex.org/W4387323024","https://openalex.org/W4387634967","https://openalex.org/W4389364446","https://openalex.org/W4389821462","https://openalex.org/W4390041933","https://openalex.org/W4392012692","https://openalex.org/W4400222256","https://openalex.org/W4402354047","https://openalex.org/W4404350186","https://openalex.org/W4404396425","https://openalex.org/W4405090824","https://openalex.org/W4405354744","https://openalex.org/W4405434146","https://openalex.org/W4405655184","https://openalex.org/W4407093326","https://openalex.org/W4407244814","https://openalex.org/W4407814980","https://openalex.org/W4407815020","https://openalex.org/W4414050442","https://openalex.org/W4414051084","https://openalex.org/W4414079054","https://openalex.org/W4414281281","https://openalex.org/W4414428140","https://openalex.org/W4414582060","https://openalex.org/W4414901575","https://openalex.org/W4414968801","https://openalex.org/W4414991724","https://openalex.org/W4415088980","https://openalex.org/W4415329948","https://openalex.org/W4415913019","https://openalex.org/W4415951582","https://openalex.org/W4416045192","https://openalex.org/W4417042701","https://openalex.org/W4417080391","https://openalex.org/W4417144670","https://openalex.org/W6966680242","https://openalex.org/W6966954010","https://openalex.org/W7103983983","https://openalex.org/W7106247592","https://openalex.org/W7115600136","https://openalex.org/W7118010205","https://openalex.org/W7160198147","https://openalex.org/W7204808299"],"related_works":["https://openalex.org/W7167614382","https://openalex.org/W6929364076","https://openalex.org/W4400612090","https://openalex.org/W7214770690","https://openalex.org/W7118004700","https://openalex.org/W7127280795","https://openalex.org/W7106290254","https://openalex.org/W7163320673","https://openalex.org/W4415951582","https://openalex.org/W7216275578"],"abstract_inverted_index":{"Embodied":[0],"Chain-of-Thought":[1],"(CoT)":[2],"reasoning":[3,19,53,71,79,95,171],"has":[4],"significantly":[5],"enhanced":[6],"Vision-Language-Action":[7],"(VLA)":[8],"models,":[9],"yet":[10],"current":[11],"methods":[12],"rely":[13],"on":[14],"rigid":[15],"templates":[16,30],"to":[17,34,68,169],"specify":[18],"primitives":[20],"(e.g.,":[21],"objects":[22],"in":[23,114,117,144,149,155,186],"the":[24],"scene,":[25],"high-level":[26],"plans,":[27],"structural":[28],"affordances).These":[29],"can":[31,89],"force":[32],"policies":[33],"process":[35],"irrelevant":[36],"information":[37],"that":[38,160,172],"distracts":[39],"from":[40,72],"critical":[41],"action-prediction":[42],"signals.This":[43],"creates":[44],"a":[45,81,93],"bottleneck:":[46],"without":[47,55,101],"successful":[48,176],"policies,":[49],"we":[50,58],"cannot":[51,59],"verify":[52],"quality;":[54],"quality":[56],"reasoning,":[57],"build":[60],"robust":[61],"policies.We":[62],"introduce":[63],"R&B-EnCoRe,":[64],"which":[65],"enables":[66,167],"models":[67,88,159,168],"bootstrap":[69],"embodied":[70],"internetscale":[73],"knowledge":[74,185],"through":[75],"self-supervised":[76],"refinement.By":[77],"treating":[78],"as":[80],"latent":[82],"variable":[83],"within":[84],"importance-weighted":[85],"variational":[86],"inference,":[87],"generate":[90],"and":[91,125,137,152],"distill":[92,170],"refined":[94],"training":[96],"dataset":[97],"of":[98,175],"embodiment-specific":[99],"strategies":[100],"external":[102],"rewards,":[103],"verifiers,":[104],"or":[105],"human":[106],"annotation.We":[107],"validate":[108],"R&B-EnCoRe":[109],"across":[110],"manipulation":[111,145],"(Franka":[112],"Panda":[113],"simulation,":[115],"WidowX":[116],"hardware),":[118],"legged":[119],"navigation":[120,150],"(bipedal,":[121],"wheeled,":[122],"bicycle,":[123],"quadruped),":[124],"autonomous":[126],"driving":[127],"embodiments":[128],"using":[129],"various":[130],"VLA":[131],"architectures":[132],"with":[133],"1B,":[134],"4B,":[135],"7B,":[136],"30B":[138],"parameters.Our":[139],"approach":[140],"achieves":[141],"28%":[142],"gains":[143],"success,":[146],"101%":[147],"improvement":[148],"scores,":[151],"21%":[153],"reduction":[154],"collision-rate":[156],"metric":[157],"over":[158],"indiscriminately":[161],"reason":[162],"about":[163],"all":[164],"available":[165],"primitives.R&B-EnCoRe":[166],"is":[173],"predictive":[174],"control,":[177],"bypassing":[178],"manual":[179],"annotation":[180],"engineering":[181],"while":[182],"grounding":[183],"internet-scale":[184],"physical":[187],"execution.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-02-11T00:00:00"}