The One RING：一个机器人室内导航通才模型
The One RING: a Robotic Indoor Navigation Generalist
AI总结：
本文提出RING，一种与机器人形态无关的室内导航通才策略，通过仿真中大规模形态随机化训练，在跨形态视觉目标导航任务上取得显著成功，并可直接部署于多种真实机器人平台。
摘要：
现代机器人在形状、尺寸以及用于感知和交互环境的传感器配置方面差异显著。然而，大多数导航策略都是特定于具体形态的——在一个机器人上训练的策略通常无法泛化到另一个机器人，即使身体尺寸或相机视角仅有微小变化。随着定制硬件日益普及，人们越来越需要一个能够跨形态泛化的统一策略，从而无需为每个特定机器人重新训练。在本文中，我们提出了RING（Robotic Indoor Navigation Generalist，机器人室内导航通才模型），一种与形态无关的策略，可将任何移动机器人转变为高效的室内语义导航器。RING完全在仿真中训练，利用对机器人形态的大规模随机化，实现对众多真实世界平台的稳健泛化。为此，我们扩展了AI2-THOR模拟器，以实例化具有可控配置的机器人，这些配置在身体尺寸、旋转枢轴点和相机参数上有所变化。在视觉目标导航任务上，RING实现了强大的跨形态（XE）泛化——在五个仿真形态上平均成功率达到72.1%（在Chores-S基准上绝对提升16.7%），在包括Stretch RE-1、LoCoBot和Unitree Go1在内的四个真实世界平台上达到78.9%——与特定形态的策略相当甚至更优。我们进一步在真实厨房环境中将RING部署到RB-Y1轮式人形机器人上，展示了其在移动操作平台上的开箱即用潜力。（项目网站：https://one-ring-policy.allen.ai）
英文摘要：
Modern robots vary significantly in shape, size, and sensor configurations used to perceive and interact with their environments. However, most navigation policies are embodiment-specific--a policy trained on one robot typically fails to generalize to another, even with minor changes in body size or camera viewpoint. As custom hardware becomes increasingly common, there is a growing need for a single policy that generalizes across embodiments, eliminating the need to retrain for each specific robot. In this paper, we introduce RING (Robotic Indoor Navigation Generalist), an embodiment-agnostic policy that turns any mobile robot into an effective indoor semantic navigator. Trained entirely in simulation, RING leverages large-scale randomization over robot embodiments to enable robust generalization to many real-world platforms. To support this, we augment the AI2-THOR simulator to instantiate robots with controllable configurations, varying in body size, rotation pivot point, and camera parameters. On the visual object-goal navigation task, RING achieves strong cross-embodiment (XE) generalization--72.1% average success rate across five simulated embodiments (a 16.7% absolute improvement on the Chores-S benchmark) and 78.9% across four real-world platforms, including Stretch RE-1, LoCoBot, and Unitree Go1--matching or even surpassing embodiment-specific policies. We further deploy RING on the RB-Y1 wheeled humanoid in a real-world kitchen environment, showcasing its out-of-the-box potential for mobile manipulation platforms. (Project website: https://one-ring-policy.allen.ai)
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。
