NUWA 风险评测 · 评测基准
ASIMOV v2: Can AI Perceive Physical Danger and Intervene?
NUWA 研究解读 · 独立复核待完成
NUWA Research Note
研究问题研究设计与假设来源发现NUWA 解读局限与相反证据研究与决策意义证据补充机构与角色原始资源模型辅助整理 · 选读原始全文或官方文章中的相关章节；尚未完成逐章节审计。
研究速读
NUWA 解读：识别描述中的危险，不能直接证明物理干预安全。
研究问题
具身模型能否识别伤害风险并遵守其身体约束？
研究设计与假设
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。
来源发现
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）。
NUWA 解读
NUWA 解读：识别描述中的危险，不能直接证明物理干预安全。
局限与相反证据
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。
研究与决策意义
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。
精确来源位置
- Can AI Perceive Physical Danger and Intervene? Thanks: {abjindal, dklakashnikov, oscarchang, divyagari, animajumdar, sindhwani}@google.com · §2 ASIMOV-2.0: A New Physical Safety BenchmarkSelected original resource https://arxiv.org/html/2509.21651; sha256:e9cdfcb13b688a5152a4c9475996663228d49e644405112f6073ceb9934e283d; archived source capture; exact capture time not independently established
- Can AI Perceive Physical Danger and Intervene? Thanks: {abjindal, dklakashnikov, oscarchang, divyagari, animajumdar, sindhwani}@google.com · §3 Evaluations and InsightsSelected original resource https://arxiv.org/html/2509.21651; sha256:e9cdfcb13b688a5152a4c9475996663228d49e644405112f6073ceb9934e283d; archived source capture; exact capture time not independently established
来源核查、数据提取、编辑批准与实验复现分别记录。 方法说明 →
证据补充 · 2026-10-28
模型辅助整理 · 独立证据及双语编辑复核待完成。以下数值为来源发现或材料计数，与趋势结果序列分开保存。
危险识别、聊天拒答、控制动作与造成损伤是不同终点。RoboHarm 说明接口变化会改变拒答表现；两种仿真基准补充不安全成功、损伤和过程成本，仍需要真实环境校准。
关联阅读
NUWA 阅读关联；不据此声称原文引用、实验复现或成绩等价。
本次解释的来源
- Refuses in Chat, Complies with Arms: LLM Refusal Does Not Survive Robot Control · Abstract; §§2–4; discussion; text lines 00044,00055,00061Original resource captured 2026-10-28T07:24:43.704880+00:00; sha256:c5b843fd1a59541e7c7713423f4c765813de1b6dc8cb85bc7aa5913c0c945572
- OopsieVerse: A Safety Benchmark with Damage-Aware Simulation for Robot Manipulation · §§III–V; limitations; text lines 00029,00303,00307,00309Original resource captured 2026-10-28T07:24:43.858466+00:00; sha256:e5c0c24c6eb494b5bef1612f1f6d5381aa9972a4aaa8937de7dcdb3e046a48d0
- ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models · §§III–V; discussion; text lines 00082,00084,00134,00141,00146,00147Original resource captured 2026-10-28T07:24:44.372873+00:00; sha256:303708eaa7bcf2e1d96cd551279703949de0dff652b1b5b86e0cd2dd5905329a
机构与角色
作者 (8)
Abhishek Jindal · Dmitry Kalashnikov · R. Alex Hofer · Oscar Chang · Divya Garikapati · Anirudha Majumdar · Pierre Sermanet · Vikas Sindhwani
评测协议
引用与复用
引用研究发现时请引用原始出版物；引用 NUWA 的整理与解释时，单独引用本站记录及对应快照。
原始出版物 · BibTeX
@misc{asimov,
title = {ASIMOV v2: Can AI Perceive Physical Danger and Intervene?},
url = {https://asimov-benchmark.github.io/v2/},
author = {Abhishek Jindal and Dmitry Kalashnikov and R. Alex Hofer and Oscar Chang and Divya Garikapati and Anirudha Majumdar and Pierre Sermanet and Vikas Sindhwani},
version = {ASIMOV v2 / arXiv:2509.21651},
note = {ASIMOV v2 / arXiv:2509.21651}
}
NUWA 记录 · BibTeX
@misc{asimov-nuwa,
title = {ASIMOV v2: Can AI Perceive Physical Danger and Intervene? — NUWA research record},
url = {https://whitzard.tech/nuwa/whitzard-index/work/asimov/},
version = {2026-10-29.1},
organization = {NUWA Frontier AI Safety Lab},
howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--asimov.json},
note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--asimov.json.}
}
证据快照 2026-10-29.1 · 索引更新 · RSS
参考文献
- [1] Abhishek Jindal, Dmitry Kalashnikov 等. Can AI Perceive Physical Danger and Intervene?. ASIMOV v2 / arXiv:2509.21651 ; Project page author affiliation list; Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification.
- [2] Abhishek Jindal, Dmitry Kalashnikov 等. Can AI Perceive Physical Danger and Intervene? Thanks: {abjindal, dklakashnikov, oscarchang, divyagari, animajumdar, sindhwani}@google.com ; §2 ASIMOV-2.0: A New Physical Safety Benchmark; §3 Evaluations and Insights