论文arXiv 2611.236853 天前
世界模型潜在安全滤波器保守性度量:独立编码器架构误拒率最低
本文由 AI 根据公开内容整理,可能有误,请以原文为准:Measuring the Conservatism of Latent Safety Filters for World Models(arXiv 2611.23685)
核心内容
针对世界模型中潜在安全滤波器因表征耦合导致过度保守的问题,研究提出Overlap指标量化特定潜在空间对滤波器的强制约束。理论证明Overlap为滤波器在完全拦截数据集中不安全转移时,必须误拒安全转移的最小比例。该指标与保形校准解耦,适用于任意潜在表征设计的安全性评估。
研究对比了基于分类器、世界模型本体及独立编码器三种安全标签训练架构。在视觉导航任务中,独立编码器方案展现出最低的Overlap值。在相同保形置信度下,该架构的安全滤波器误拒安全动作数量最少,使规划器能够到达最多的目标点,验证了低Overlap表征在保障安全的同时能显著提升具身智能体的任务执行效率。
关键看点
- Overlap指标定义:将相似潜在状态与动作分组为单元,定义为包含不安全转移单元内安全转移的占比,是滤波器零漏报时的理论最小误拒率。
- 架构对比实验:在视觉导航任务中测试三种安全表征设计,独立编码器架构相比分类器与世界模型本体方案具有最低的Overlap值。
- 任务性能关联:在同等保形校准水平下,低Overlap的独立编码器滤波器误拒安全动作最少,使规划器达成目标数量最多,兼顾安全性与通过率。
- 通用评估框架:Overlap度量与保形校准阈值设定相互独立,可作为正交指标用于评估任意世界模型潜在空间对安全决策的内在约束程度。
工程与产业观察
该研究为具身智能安全模块提供了表征层面的量化评估工具。工程实践表明,在设计世界模型安全滤波器时,不应仅关注保形校准阈值,更应优先选择低Overlap的潜在空间架构(如独立编码器)。这能在不牺牲统计安全保证的前提下,显著降低因表征缺陷导致的策略保守性,提升机器人在复杂环境中的实际作业成功率。
英文摘要 (Abstract)
A latent safety filter decides from the latent of a world model whether a planned action is safe. Conformal calibration sets the threshold of the filter so that it accepts an unsafe action only with a small probability. However, the filter can still be conservative and refuse many safe actions, depending on the latent. To measure the conservatism that a latent forces on the filter, we group similar latents and actions into cells. A filter that gives one decision per cell can refuse the unsafe transitions of a cell only by refusing the safe ones in it as well. We call the share of safe transitions that lie in such cells the overlap. We prove that the overlap is the minimum share of safe transitions that such a filter has to refuse in order to accept no unsafe transition in the data. Both the overlap and the conformal calibration can be applied to any latent. We use this to compare three existing designs, in which the safety labels train a classifier on top of the world model, the world model itself, or a separate encoder beside it. In a visual navigation task, the separate encoder has the lowest overlap, and at the same conformal level its filter refuses the fewest safe actions and lets the planner reach the most goals of the three.
作者:Johannes Mootz, Mani Amani, Reza Akhavian
外部来源
本页事实对应的公开页面,以原文为准。(点击将离开本站)