Fetch My Beer: 面向平滑抓取-放置的合成到真实分层策略
Fetch My Beer: Synthetic-to-real Hierarchical Policy for Smooth Pick-and-place
浏览论文内容
中文总结 AI 辅助
针对液体容器稳定运输任务，提出合成到真实的分层扩散策略，结合物理验证数据生成与潜在空间规划，实现平滑稳定的抓取-放置，优于现有方法。
中文摘要 AI 辅助
许多现实世界的机器人应用需要动态敏感的操作，其成功不仅取决于达到目标状态，还取决于在整个执行过程中保持稳定的物体动态。我们研究了液体容器的稳定运输问题，其中机器人必须将物体移动到目标位置，同时抑制晃动并防止溢出。与传统的抓取-放置不同，该任务对运动平滑性和轨迹级稳定性提出了严格要求，暴露了现有系统的明显局限性。具体而言，流体模拟对于在线强化学习而言成本过高；人类遥操作在模仿学习过程中会引入意外加速度，导致晃动；当前策略流程优化的是任务完成而非动态稳定性。我们提出了一种合成到真实框架，将经过物理验证的数据生成与分层、基于扩散的控制器相结合。可扩展的数据流程合成抓取，通过视觉语言模型过滤不稳定姿态，并通过流体模拟验证运输轨迹。该策略由一个高层模块组织，该模块将语言和视觉观察转换为SE(3)控制目标，以及一个潜在扩散控制器，该控制器首先在紧凑的潜在空间中高效规划，然后解码密集动作块，从而实现平滑稳定运动所需的高控制频率。大量实验表明，我们的系统在运输平滑性和动态稳定性方面优于最先进的操作策略。我们的项目页面：此https URL
英文摘要
Many real-world robotic applications require dynamically sensitive manipulation, where success depends not only on reaching a target state but on maintaining stable object dynamics throughout execution. We study the stable transport of liquid-filled containers, where a robot must move objects to target locations while suppressing sloshing and preventing spillage. Unlike conventional pick-and-place, this task imposes stringent requirements on motion smoothness and trajectory-level stability, exposing clear limitations in existing systems. Specifically, fluid simulation remains too costly for online reinforcement learning; human teleoperation introduces unintended accelerations that induce sloshing during imitation learning; and current policy pipelines optimize for task completion rather than dynamic stability. We propose a synthetic-to-real framework coupling physically validated data generation with a hierarchical, diffusion-based controller. The scalable data pipeline synthesizes grasps, filters unstable poses via a vision-language model, and validates transport trajectories through fluid simulation. The policy is organized with a high-level module that translates language and visual observations into SE(3) control targets, and a latent diffusion controller that first plans efficiently in a compact latent space and then decodes dense action chunks, enabling the high control frequency needed for smooth and stable motion. Extensive experiments show our system outperforms state-of-the-art manipulation policies in transport smoothness and dynamic stability. Our project page: https://fetch-my-beer.github.io/
发表机构
- Tsinghua University（清华大学）
- ETH Zurich（苏黎世联邦理工学院）
- Beijing Xiaomi Robot Technology Co., Ltd（北京小米机器人技术有限公司）
- Technical University of Munich（慕尼黑工业大学）
机构由 AI 辅助整理，请以论文原文为准。
