学习以视角不变潜动作实现鲁棒行动
Learning to Act Robustly with View-Invariant Latent Actions
把跨轨迹的转移模式压缩成潜动作，并用真实动作序列做引导对齐，为视觉表征注入物理动力学约束；做具身策略或需要视角鲁棒表征时，可把这一潜动作对齐目标当作预训练任务复用。
原文依据 models a latent action capturing transition patterns across trajectories to learn view-invariant representations grounded in physical dynamics
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于视觉的机器人策略往往连轻微的视角变化都难以应对，这凸显了对视角不变视觉表征的需求。在真实环境中，视角变化不可避免，且会显著破坏策略性能，这一挑战更为突出。现有方法通常从场景级的多视角观测中学习不变性，但这类方法依赖视觉外观，未能纳入对鲁棒泛化至关重要的物理动力学。我们提出视角不变潜动作（VILA），它建模一种潜动作，用以捕捉跨轨迹的转移模式，从而学习以物理动力学为基础的视角不变表征。VILA 借助基于真实动作序列的动作引导目标，在不同视角之间对齐这些潜动作。仿真与真实世界中的实验表明，基于 VILA 的策略能有效泛化到未见视角，并良好迁移到新任务，确立了 VILA 作为一个强预训练框架的地位，它提升了对视角变化的鲁棒性以及下游学习性能。
英文原文摘要 1134 字符
Vision-based robotic policies often struggle with even minor viewpoint changes, underscoring the need for view-invariant visual representations. This challenge becomes more pronounced in real-world settings, where viewpoint variability is unavoidable and can significantly disrupt policy performance. Existing methods typically learn invariance from multi-view observations at the scene level, but such approaches rely on visual appearance and fail to incorporate the physical dynamics essential for robust generalization. We propose View-Invariant Latent Action (VILA), which models a latent action capturing transition patterns across trajectories to learn view-invariant representations grounded in physical dynamics. VILA aligns these latent actions across viewpoints using an action-guided objective based on ground-truth action sequences. Experiments in both simulation and the real world show that VILA-based policies generalize effectively to unseen viewpoints and transfer well to new tasks, establishing VILA as a strong pretraining framework that improves resilience to viewpoint shifts and downstream learning performance.