基于物理世界模型的机器人学习
Robot Learning from a Physical World Model
AI总结：
该研究提出PhysWorld框架，通过结合视频生成与物理世界重建，将生成视频中的视觉演示转化为物理准确的机器人动作，实现零样本泛化且无需真实机器人数据，显著提升操作精度。
摘要：
我们提出PhysWorld框架，该框架通过物理世界建模使机器人能够从视频生成中学习。近期的视频生成模型可从语言指令和图像中合成逼真的视觉演示，为机器人学提供了强大但未被充分探索的训练信号来源。然而，直接将生成视频中的像素运动重定向到机器人会忽略物理规律，常导致操作不准确。PhysWorld通过将视频生成与物理世界重建相结合来解决这一局限。给定单张图像和任务指令，我们的方法生成任务条件视频并从视频中重建底层物理世界，生成的视频运动通过基于对象的残差强化学习与物理世界模型结合，转化为物理上准确的动作。这种协同作用将隐式视觉引导转化为可物理执行的机器人轨迹，无需真实机器人数据收集，实现零样本可泛化的机器人操作。在多种真实世界任务上的实验表明，PhysWorld相比以往方法显著提高了操作精度。详情请访问项目网页：https://pointscoder.github.io/PhysWorld_Web/
英文摘要：
We introduce PhysWorld, a framework that enables robot learning from video generation through physical world modeling. Recent video generation models can synthesize photorealistic visual demonstrations from language commands and images, offering a powerful yet underexplored source of training signals for robotics. However, directly retargeting pixel motions from generated videos to robots neglects physics, often resulting in inaccurate manipulations. PhysWorld addresses this limitation by coupling video generation with physical world reconstruction. Given a single image and a task command, our method generates task-conditioned videos and reconstructs the underlying physical world from the videos, and the generated video motions are grounded into physically accurate actions through object-centric residual reinforcement learning with the physical world model. This synergy transforms implicit visual guidance into physically executable robotic trajectories, eliminating the need for real robot data collection and enabling zero-shot generalizable robotic manipulation. Experiments on diverse real-world tasks demonstrate that PhysWorld substantially improves manipulation accuracy compared to previous approaches. Visit \href{https://pointscoder.github.io/PhysWorld_Web/}{the project webpage} for details.
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。
