重新思考通用机器人的安全性
Rethinking Safety for Generalist Robots
浏览论文内容
中文总结 AI 辅助
本文提出通用机器人需从传统物理安全转向具身AI安全，涵盖情境、意图等风险，并给出分类学与全栈研究议程以指导安全部署。
中文摘要 AI 辅助
通用机器人有望改变我们的社会：同一系统既能准备餐食或折叠衣物，也可能修理汽车、检查基础设施或照料亲人。然而，这种多功能性引入了远超长期主导机器人学的基于碰撞和力的安全概念的风险。安全概念现在必须考虑情境（例如，关闭建筑物的电力仅在计划维护期间是安全的）、用户意图（例如，要求机器人“清洁厨房”包含未言明的期望，即机器人不应混合漂白剂和氨水等危险但强效的清洁剂）、难以建模的物理后果（例如，在备餐过程中烧焦食物）等。我们认为需要开启机器人安全的新时代——具身AI安全——在机器人生命周期中拓宽所考虑的危险，同时认识到比特的安全不能与原子的安全分离。我们提出了新兴风险的分类学和全栈研究议程，以指导通用机器人的安全部署。
英文摘要
Generalist robots promise to transform our society: the same system that prepares a meal or folds laundry might also repair a car, inspect infrastructure, or care for a loved one. Yet this versatility introduces risks far beyond the collision- and force-based safety notions that have long dominated robotics. Notions of safety must now consider context (e.g., turning off a building's electricity is only safe during scheduled maintenance), user intent (e.g., asking the robot to ``clean the kitchen'' includes unspoken expectations that the robot should not mix dangerous but powerful cleaning agents like bleach and ammonia), hard-to-model physical consequences (e.g., burning food during meal preparation), and more. We argue the need for a new era of robot safety---embodied AI safety---that broadens the hazards considered across the robot's lifecycle while recognizing that the safety of bits cannot be separated from the safety of atoms. We present a taxonomy of emerging risks and a full-stack research agenda to guide the safe deployment of generalist robots.
发表机构
- Stanford University（斯坦福大学）
- University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
- NVIDIA Research（英伟达研究院）
- Princeton University（普林斯顿大学）
- Carnegie Mellon University（卡内基梅隆大学）
机构由 AI 辅助整理，请以论文原文为准。
