从单实例RGB演示中学习类别级最后米导航
Learning Category-level Last-meter Navigation from RGB Demonstrations of a Single-instance
AI总结：
提出面向对象的模仿学习框架，利用RGB观测实现四足移动机械臂在最后米阶段的精确导航，无需深度或地图先验，在类别级泛化中达到高成功率。
摘要：
移动机械臂基座的精确定位对于后续成功操作至关重要。大多数基于RGB的导航系统仅保证粗略的米级精度，不适合移动操作的精确定位阶段。这一差距导致操作策略无法在其训练演示的分布内运行，从而导致频繁的执行失败。我们通过引入一种面向对象的模仿学习框架来解决这一差距，用于最后米导航，使四足移动机械臂机器人仅使用其机载摄像头的RGB观测即可实现可操作的定位。我们的方法将导航策略条件化为三个输入：目标图像、来自机载摄像头的多视角RGB观测以及指定目标对象的文本提示。然后，语言驱动的分割模块和空间得分矩阵解码器提供显式的对象定位和相对姿态推理。使用类别内单个对象实例的真实世界数据，该系统能够泛化到不同环境中具有挑战性光照和背景条件的未见对象实例。为了全面评估这一点，我们引入了两个指标：边缘对齐度量（使用真实方向）和对象对齐度量（评估机器人视觉上面对目标的程度）。在这些指标下，我们的策略在相对于未见目标对象定位时，边缘对齐成功率达到74.58%，对象对齐成功率达到89.42%。这些结果表明，无需深度、LiDAR或地图先验，即可在类别级实现精确的最后米导航，为统一的移动操作提供可扩展的途径。项目页面：此https URL
英文摘要：
Achieving precise positioning of the mobile manipulator's base is essential for successful manipulation actions that follow. Most of the RGB-based navigation systems only guarantee coarse, meter-level accuracy, making them less suitable for the precise positioning phase of mobile manipulation. This gap prevents manipulation policies from operating within the distribution of their training demonstrations, resulting in frequent execution failures. We address this gap by introducing an object-centric imitation learning framework for last-meter navigation, enabling a quadruped mobile manipulator robot to achieve manipulation-ready positioning using only RGB observations from its onboard cameras. Our method conditions the navigation policy on three inputs: goal images, multi-view RGB observations from the onboard cameras, and a text prompt specifying the target object. A language-driven segmentation module and a spatial score-matrix decoder then supply explicit object grounding and relative pose reasoning. Using real-world data from a single object instance within a category, the system generalizes to unseen object instances across diverse environments with challenging lighting and background conditions. To comprehensively evaluate this, we introduce two metrics: an edge-alignment metric, which uses ground truth orientation, and an object-alignment metric, which evaluates how well the robot visually faces the target. Under these metrics, our policy achieves 74.58% success in edge-alignment and 89.42% success in object-alignment when positioning relative to unseen target objects. These results show that precise last-meter navigation can be achieved at a category-level without depth, LiDAR, or map priors, enabling a scalable pathway toward unified mobile manipulation. Project page: https://rpm-lab-umn.github.io/category-level-last-meter-nav/
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。
