SID：滑入分布以实现鲁棒的少样本操控
SID: Sliding into Distribution for Robust Few-Demonstration Manipulation
AI总结：
SID通过学习对象中心运动场，使系统在少样本下鲁棒地滑向演示 manifold 和轻量执行策略的可靠区域，提升动态扰动下的操控性能。
摘要：
在物体姿态、视角和动态扰动下，机器人操控的泛化极具挑战性，尤其在仅有少量演示时。端到端视觉-运动策略虽表达能力强但数据需求高，而规划与优化虽能满足显式约束但无法直接捕捉人类交互策略。我们提出滑入分布（SID），一种结构化框架，通过标准化演示学习对象中心运动场，使系统迭代滑向演示 manifold 并进入轻量自体中心执行策略的可靠操作区域，缓解离分布（OOD）执行问题。运动场在远离演示 manifold 时提供大修正动作，自然消失于收敛附近，使在显著姿态和视角变化下实现稳健到达。在到达范围内，通过条件流匹配训练的自体中心策略执行任务特定操控，辅以运动学一致点云重投影增强，保持动作-观察一致性。在六个现实任务中，SID 在仅有两个演示时，约90%的成功率，受干扰时成功率下降10%。总体而言，SID 提供了一种新的少样本操控范式：通过在线分布恢复显式管理分布偏移。
英文摘要：
Generalizing robotic manipulation across object poses, viewpoints, and dynamic disturbances is difficult, especially with only a few demonstrations. End-to-end visuomotor policies are expressive but data-hungry, while planning and optimization satisfy explicit constraints but do not directly capture the interaction strategies demonstrated by humans. We propose Sliding into Distribution (SID), a structured framework that learns an object-centric motion field from canonicalized demonstrations to iteratively slide the system toward the demonstrated manifold and into the reliable operating region of a lightweight egocentric execution policy, mitigating out-of-distribution (OOD) execution. The motion field provides large corrective motions when far from the demonstration manifold and naturally vanishes near convergence, enabling robust reaching under substantial pose and viewpoint shifts. Within the reached regime, an egocentric policy trained with conditioned flow matching performs task-specific manipulation, supported by kinematically consistent point-cloud reprojection augmentation that preserves action-observation consistency. Across six real-world tasks, SID achieves approximately 90% success under OOD initializations with only two demonstrations, with under a 10% drop under distractors and external disturbances. Overall, SID provides a new paradigm for few-shot manipulation: explicitly managing distribution shift via online distribution recovery.
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。
