让机器人安全执行自然语言指令，自动适配不同安全要求。
Towards General Language-Conditioned Latent Safety Filters
- 用自然语言控制安全规则，动态调整机器人的行为边界。
- 实验显示约束违规率下降，能部分适应未见过的安全要求。
- 适合需要灵活安全策略的机器人应用，如家庭服务、工业协作。
机器人策略正变得越来越通用，视觉-语言-动作（VLA）模型使单一策略能执行由自然语言指定的多样化任务。然而，安全部署不仅需适应新任务，还需应对用户、环境和应用场景间变化的安全需求。现有安全过滤器多针对特定约束，当安全要求改变时需重新设计或重学。本文研究语言条件下的安全过滤，将哈密顿-雅可比安全智能体与评论家基于自然语言指定的约束进行条件化。我们在基于视觉的抓取-放置、擦桌和积木堆叠任务中评估该方法，检验其对语言指定约束的执行能力及在已评估约束族内未见约束实例上的迁移能力。实验表明，语言条件安全过滤器能有效降低约束违规，并展现出对未见约束实例的部分迁移能力。
原文摘要 · Abstract (English)
Robot policies are becoming increasingly general, with vision-language-action (VLA) models enabling a single policy to execute diverse tasks specified in natural language. Safe deployment, however, requires adapting not only to new tasks but also to varying safety requirements across users, environments, and applications. Existing safety filters remain largely constraint-specific and thus must be redesigned or relearned when safety requirements change. In this paper, we investigate language-conditioned safety filtering, in which a Hamilton-Jacobi safety actor and critic are conditioned on language-specified constraints. We evaluate this formulation across pick-and-place, table-wiping, and block-stacking tasks in the vision-based setting, examining its ability to enforce language-specified constraints and transfer to unseen constraint instances within the evaluated constraint families. Our experiments provide evidence that language-conditioned safety filters reduce constraint violations and exhibit partial transfer to unseen constraint instances.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。