AI 中文总结
该研究提出语言条件安全过滤器，结合哈密顿-雅可比安全演员与评论家，在多种视觉机器人任务中减少约束违规并实现部分未见过约束实例的迁移。
AI 中文摘要
机器人策略正变得越来越通用，视觉-语言-动作（VLA）模型使单个策略能够执行自然语言指定的各种任务。然而，安全部署不仅需要适应新任务，还需要适应用户、环境和应用场景中不断变化的安全要求。现有的安全过滤器在很大程度上仍针对特定约束，因此当安全要求发生变化时，必须重新设计或重新学习。在本文中，我们研究语言条件安全过滤，其中哈密顿-雅可比安全演员与评论家以语言指定的约束为条件。我们在基于视觉的场景中，对抓取放置、擦桌子和积木堆叠任务评估该公式，检查其执行语言指定约束以及在评估的约束族内对未见过的约束实例的迁移能力。我们的实验提供证据表明，语言条件安全过滤器可减少约束违规，并对未见过的约束实例表现出部分迁移能力。
英文摘要
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.
