Pose6DAug: 用于机器人数据增强的物理合理多视图物体替换
Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation
AI总结：
提出Pose6DAug，一种基于失败驱动的数据增强框架，通过3D网格和6D姿态轨迹替换成功轨迹中的物体，生成多视图一致的物理合理演示，无需额外数据收集，在新型物体上提升VLA策略成功率16.5%。
摘要：
视觉-语言-动作（VLA）策略在通用操作中展现出强大潜力，但在外观或几何形状偏离训练分布的新型分布外物体上常常失败。标准的补救措施是为每个失败案例收集多视图遥操作数据，但这在成本和时间上扩展性差。我们提出Pose6DAug，一种失败驱动的数据增强框架，将策略自身的成功回合转化为针对其失败模式的目标演示，无需任何新数据收集。我们的关键洞察是，每个成功回合已经编码了一个物理有效的动作轨迹以及校准的多视图观测。通过仅替换被操作物体同时保留该轨迹，我们获得新的且物理基础的演示。然而，简单的2D视频编辑会破坏多视图一致性和物理合理性，特别是在严重遮挡和以自我为中心的视角下。我们的方法直接在3D中操作，通过时间一致的6D姿态轨迹驱动的显式网格锚定目标物体，确保所有相机视图的几何一致渲染。在我们方法增强的数据上微调VLA，相对于最先进的基线，在新型物体上的成功率提高了16.5%，同时保持了分布内性能。这些结果表明，多视图和物理一致的增强是实现可扩展VLA泛化的实用途径。
英文摘要：
Vision-language-action (VLA) policies have shown strong potential for general-purpose manipulation, yet they often fail on novel, out-of-distribution objects whose appearance or geometry deviates from the training distribution. The standard remedy is to collect multi-view teleoperation data for every failure case, but this scales poorly in both cost and time. We introduce Pose6DAug, a failure-driven data augmentation framework that turns a policy's own successful episodes into targeted demonstrations for its failure modes, without any new data collection. Our key insight is that each successful episode already encodes a physically valid action trajectory together with calibrated multi-view observations. By swapping only the manipulated object while preserving this trajectory, we obtain new and physically grounded demonstrations. However, naive 2D video editing breaks multi-view consistency and physical plausibility, particularly under heavy occlusion and egocentric viewpoints. Our method instead operates directly in 3D, anchoring the target object with an explicit mesh driven by a temporally coherent 6D pose trajectory, ensuring geometrically consistent renderings across all camera views. Fine-tuning a VLA on data augmented by our method improves success rates by 16.5% relative to the state-of-the-art baseline on novel objects, while preserving in-distribution performance. These results show that multi-view and physically consistent augmentation is a practical path to scalable VLA generalization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
