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 learned using one robot's configuration does not typically gracefully generalize to another. Even small changes in the body size or camera viewpoint may cause failures. With the recent surge in custom hardware developments, it is necessary to learn a single policy that can be transferred to other embodiments, eliminating the need to (re)train for each specific robot. In this paper, we introduce RING (Robotic Indoor Navigation Generalist), an embodiment-agnostic policy, trained solely in simulation with diverse randomly initialized embodiments at scale. Specifically, we augment the AI2-THOR simulator with the ability to instantiate robot embodiments with controllable configurations, varying across body size, rotation pivot point, and camera configurations. In the visual object-goal navigation task, RING achieves robust performance on real unseen robot platforms (Stretch RE-1, LoCoBot, Unitree's Go1), achieving an average of 72.1% and 78.9% success rate across 5 embodiments in simulation and 4 robot platforms in the real world. (project website: https://one-ring-policy.allen.ai/)

翻译：现代机器人在形态、尺寸以及用于感知和交互的传感器配置方面差异显著。然而，大多数导航策略是针对特定机器人形态设计的；基于一种机器人配置学习的策略通常无法优雅地迁移到其他形态。即使是机身尺寸或摄像头视角的微小变化也可能导致失败。随着近期定制硬件开发的激增，有必要学习一种能够迁移到其他形态的单一策略，从而无需为每个特定机器人（重新）训练。本文提出RING（Robotic Indoor Navigation Generalist），一种与机器人形态无关的策略，完全在仿真环境中通过大规模随机初始化的多样化形态进行训练。具体而言，我们扩展了AI2-THOR仿真器，使其能够实例化具有可控配置的机器人形态，这些配置在机身尺寸、旋转支点和摄像头设置方面各不相同。在视觉目标导航任务中，RING在真实未见过的机器人平台（Stretch RE-1、LoCoBot、Unitree Go1）上实现了鲁棒性能，在仿真中的5种形态和现实世界中的4种机器人平台上分别达到平均72.1%和78.9%的成功率。（项目网站：https://one-ring-policy.allen.ai/）