DockAnywhere: 通过新颖的示范生成实现移动操作的数据高效视觉-运动策略学习
DockAnywhere: Data-Efficient Visuomotor Policy Learning for Mobile Manipulation via Novel Demonstration Generation
AI总结：
本文提出DockAnywhere方法，通过解耦基座运动与不变的 manipulation 技能，提升移动操作在不同 docking 点下的视角泛化能力，实验表明其显著提高了策略成功率和泛化能力。
摘要：
移动操作是使机器人在家庭和工厂等广阔环境中交互的基础能力。大多数现有方法采用两阶段范式，机器人首先导航到 docking 点，然后使用强大的视觉-运动策略进行固定基座操作。然而，现实中的移动操作常因 docking 点的位移而面临视角泛化问题。为此，我们提出了一种名为 DockAnywhere 的新颖低成本示范生成框架，通过将单个示范提升到多种可行的 docking 配置，从而在 docking 变异性下提升视角泛化能力。具体而言，DockAnywhere 通过解耦依赖 docking 的基座运动与在不同视角下保持不变的 manipulation 技能，将轨迹提升到任何可行的 docking 点。可行的 docking 候选方案在可行性约束下被采样，对应的轨迹通过结构保持增强生成。通过将机器人和物体表示为点云并应用点级空间编辑，合成视觉观测以确保观测和动作在不同视角下的一致性。在 ManiSkill 和真实世界平台上的大量实验表明，DockAnywhere 显著提高了策略成功率，并且在训练期间能够轻松泛化到从未见过的 docking 点的新视角，显著增强了移动操作策略在现实部署中的泛化能力。
英文摘要：
Mobile manipulation is a fundamental capability that enables robots to interact in expansive environments such as homes and factories. Most existing approaches follow a two-stage paradigm, where the robot first navigates to a docking point and then performs fixed-base manipulation using powerful visuomotor policies. However, real-world mobile manipulation often suffers from the view generalization problem due to shifts of docking points. To address this issue, we propose a novel low-cost demonstration generation framework named DockAnywhere, which improves viewpoint generalization under docking variability by lifting a single demonstration to diverse feasible docking configurations. Specifically, DockAnywhere lifts a trajectory to any feasible docking points by decoupling docking-dependent base motions from contact-rich manipulation skills that remain invariant across viewpoints. Feasible docking proposals are sampled under feasibility constraints, and corresponding trajectories are generated via structure-preserving augmentation. Visual observations are synthesized in 3D space by representing the robot and objects as point clouds and applying point-level spatial editing to ensure the consistency of observation and action across viewpoints. Extensive experiments on ManiSkill and real-world platforms demonstrate that DockAnywhere substantially improves policy success rates and easily generalizes to novel viewpoints from unseen docking points during training, significantly enhancing the generalization capability of mobile manipulation policy in real-world deployment.
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。
