发表机构
University of California, Davis; University of California, San Diego（加州大学戴维斯分校; 加州大学圣迭戈分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出用零阶保持和采样调度特征（陈旧度、刷新时间）处理异步传感器观测，在三种因果耦合场景下验证了刷新时间仅在影响系统状态时有效，为世界模型设计提供了指导。
AI 中文摘要
学习到的世界模型通常假设观测是同步到达的，这一抽象继承自模拟器，模拟器在每个环境步骤返回完整的状态向量。然而，物理传感以异构速率运行，在任意给定时刻，大多数观测通道都是过时的。对过时通道进行插值会引入从未被观测到的测量值，而降采样到最慢的传感器则会丢弃有效的测量值。一个自然的替代方案是采用零阶保持器保留最近一次的读数，并通过两个特征（陈旧度和刷新时间）将已知的采样调度提供给模型。我们使用Transformer世界模型在三种因果耦合递增的场景下测试了这一预测：连续控制运动中的开环滚动预测、闭环模型预测规划（其中每个学习到的模型作为规划器动力学）、以及一个线性锁存执行器系统（其中刷新事件将零阶保持的命令施加到被控对象上）。我们的研究结果表明，刷新时间的有效性取决于采样调度的因果作用，特别是当刷新事件影响系统而非仅仅报告其状态时。这些结果确立了在异步物理观测下，采样调度何时能为预测性世界模型提供有用信息。
英文摘要
Learned world models typically assume that observations arrive synchronously, an abstraction inherited from simulators that return a complete state vector at each environment step. Physical sensing instead operates at heterogeneous rates, leaving most observation channels stale at any given instant. Interpolating stale channels introduces measurements that were never observed, while downsampling to the slowest sensor discards valid measurements. A natural alternative is to zero-order-hold the most recent reading and provide the known sampling schedule to the model through two features, staleness and time-to-refresh. We test this prediction using transformer world models across three regimes of increasing causal coupling: open-loop rollouts in continuous-control locomotion, closed-loop model-predictive planning in which each learned model serves as the planner dynamics, and a linear latched-actuator system in which refresh events apply a zero-order-held command to the plant. Our findings show that the effectiveness of time-to-refresh depends on the causal role of the sampling schedule, specifically when refresh events affect the system rather than merely report its state. These results establish when sampling schedules provide useful information for predictive world models operating under asynchronous physical observations.
Comments13 pages, 2 figures. All authors contributed equally
