{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"asimov","title":"ASIMOV v2: Can AI Perceive Physical Danger and Intervene?","aliases":["ASIMOV v2"],"authors":["Abhishek Jindal","Dmitry Kalashnikov","R. Alex Hofer","Oscar Chang","Divya Garikapati","Anirudha Majumdar","Pierre Sermanet","Vikas Sindhwani"],"primaryFunction":"evaluation","secondaryFunctions":[],"kind":"benchmark","sourceId":"asimov","attributionSourceId":"asimov-author-source","originalUrl":"https://asimov-benchmark.github.io/v2/","publicationDate":null,"updatedOn":"2026-10-25","areas":["autonomous-physical-harm"],"scopeNote":{"en":"Primary dimension follows the source’s measured construct. Metric-level interpretations may differ.","zh":"主维度依据来源实际测量的构念；具体指标可能属于其他维度。"},"protocolIds":["asimov"],"contributions":[{"organizationId":"deepmind","role":"research","sourceId":"asimov","locator":"Project page author affiliation list"},{"organizationId":"princeton","role":"research","sourceId":"asimov","locator":"Project page author affiliation list"}],"summary":{"en":"Perception of physical danger and safety interventions.","zh":"物理危险感知与安全干预。"},"note":{"question":{"en":"Multimodal safety reasoning on generated scenes.","zh":"生成场景上的多模态安全推理。"},"method":{"en":"Model interpreting multimodal physical-risk scenes","zh":"解读多模态物理风险场景的模型"},"finding":{"en":"Perception of physical danger and safety interventions.","zh":"物理危险感知与安全干预。"},"supports":null,"limits":{"en":"Scene-based reasoning does not certify a deployed robot's physical safety.","zh":"场景推理不构成部署机器人物理安全认证。"},"connections":null},"resources":[],"noteStatus":{"question":"limited","method":"limited","finding":"limited","supports":"limited","limits":"limited","connections":"limited"},"noteAvailability":{"en":"Existing source-specific draft sections are retained with limited review status. A complete methods, findings and limitations check remains pending; generic sections were omitted.","zh":"已有的来源相关草稿章节予以保留，审核状态为有限核查。完整的方法、发现与限制核查仍待完成；通用套话章节已省略。"},"noteSourceLocator":"Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification.","tags":[]},"reading":{"id":"asimov","title":"ASIMOV v2: Can AI Perceive Physical Danger and Intervene?","en":{"question":"Can embodied models recognize injury risks and obey embodiment-specific safety constraints?","design":"ASIMOV-2.0 derives text scenarios from injury narratives and constraints, then generates image/video variants; recognition and intervention are separate tasks.","findings":["Three leading models averaged 92.3% text latent-risk accuracy and 88.7% high-severity accuracy in the reported comparison.","Smaller variants had material gaps from their corresponding larger models (§3)."],"interpretation":"NUWA interpretation: recognizing a described danger is evidence about perception, not validated safe physical intervention.","limits":"Generative stimuli and scenario judgments do not establish closed-loop robot safety; the selected reading does not audit synthetic-image fidelity.","decisionRelevance":"Model recommendation: retain modality, model variant and intervention task when using these results to select embodied-system tests.","takeaway":"NUWA interpretation: recognizing a described danger is evidence about perception, not validated safe physical intervention.","connections":[],"scoring":"Separate accuracy measures for latent-risk recognition and high-severity judgments; intervention is a different task.","conditions":"Text, image and video conditions and embodiment-specific constraints must remain separate.","statistics":"Three leading models averaged 92.3% text latent-risk accuracy and 88.7% high-severity accuracy in the reported comparison. Smaller variants had material gaps from their corresponding larger models (§3).","usage":"Model recommendation: retain modality, model variant and intervention task when using these results to select embodied-system tests."},"zh":{"question":"具身模型能否识别伤害风险并遵守其身体约束？","design":"ASIMOV-2.0 从伤害叙述和约束构造文本，再生成图像与视频；区分风险识别与干预。","findings":["所列三个领先模型的文本潜在风险识别平均为92.3%，高严重性识别为88.7%。","小型版本与对应大型模型存在明显差距（§3）。"],"interpretation":"NUWA 解读：识别描述中的危险，不能直接证明物理干预安全。","limits":"生成场景不能确立闭环机器人安全；此次选读未审查合成图像保真度。","decisionRelevance":"模型建议：使用结果设计具身测试时，保留模态、模型版本和干预任务区别。","takeaway":"NUWA 解读：识别描述中的危险，不能直接证明物理干预安全。","connections":[],"scoring":"潜在风险识别与高严重性判断分别计正确率，干预是另一任务。","conditions":"文本、图像、视频及身体特定约束须分开。","statistics":"所列三个领先模型的文本潜在风险识别平均为92.3%，高严重性识别为88.7%。 小型版本与对应大型模型存在明显差距（§3）。","usage":"模型建议：使用结果设计具身测试时，保留模态、模型版本和干预任务区别。"},"assertionPolicy":{"question":"source-research-question","design":"source-finding","findings":"source-finding","interpretation":"nuwa-interpretation","limits":"source-limit-or-explicit-editorial-scope-limit","connections":"source-supported-relationship-only","decisionRelevance":"model-recommendation-not-source-conclusion"},"sourceRefs":[{"sourceId":"asimov-author-source","url":"https://arxiv.org/html/2509.21651","locator":"§2 ASIMOV-2.0: A New Physical Safety Benchmark","version":"Selected original resource https://arxiv.org/html/2509.21651; sha256:e9cdfcb13b688a5152a4c9475996663228d49e644405112f6073ceb9934e283d; archived source capture; exact capture time not independently established","artifactSha256":"e9cdfcb13b688a5152a4c9475996663228d49e644405112f6073ceb9934e283d"},{"sourceId":"asimov-author-source","url":"https://arxiv.org/html/2509.21651","locator":"§3 Evaluations and Insights","version":"Selected original resource https://arxiv.org/html/2509.21651; sha256:e9cdfcb13b688a5152a4c9475996663228d49e644405112f6073ceb9934e283d; archived source capture; exact capture time not independently established","artifactSha256":"e9cdfcb13b688a5152a4c9475996663228d49e644405112f6073ceb9934e283d"}],"publication":{"state":"published","publishedOn":"2026-10-29","authorizationReference":"user-authorized-global-index-publication-2026-10-29","reviewedCandidateId":"local-6efe31bc4a0c0f37"},"review":{"state":"published-note","sourceScope":"full-text","availableScope":null,"readingCoverage":"selected-source-sections; not a complete section-by-section paper audit","completePaperAudit":false,"independentEvidenceReview":"pending-human-review","bilingualEditorialReview":"pending-human-review","authorship":"model-assisted-research-note","preparedFingerprint":"94b522bf382a2cb8da21f626da07c6391569d21d280a6fca5d366b12cbe6db6a"}},"sources":[{"id":"asimov","title":"Can AI Perceive Physical Danger and Intervene?","url":"https://asimov-benchmark.github.io/v2/","version":"ASIMOV v2 / arXiv:2509.21651","publicationDate":null,"datePrecision":"day","type":"benchmark","verifiedOn":"2026-10-24","documentId":"https://asimov-benchmark.github.io/v2","authors":["Abhishek Jindal","Dmitry Kalashnikov","R. Alex Hofer","Oscar Chang","Divya Garikapati","Anirudha Majumdar","Pierre Sermanet","Vikas Sindhwani"]}]}