OpenObject-NAV：基于动态载体关系场景图的开放词汇面向对象导航
OpenObject-NAV: Open-Vocabulary Object-Oriented Navigation Based on Dynamic Carrier-Relationship Scene Graph
AI总结：
本文提出基于动态载体关系场景图（CRSG）的开放词汇实例导航方法，结合马尔可夫决策过程与大型语言模型常识，实现高效导航至移动目标。
摘要：
在日常生活中，像杯子这样常用的物品往往没有固定的位置，且同一类别内有多个实例，它们的载体也经常发生变化。因此，机器人高效导航至特定实例变得极具挑战性。为应对这一挑战，机器人必须捕捉并持续更新场景变化与规划。然而，当前的对象导航方法主要关注语义层面，缺乏动态更新场景表示的能力。本文捕捉了常用物品与其静态载体之间的关系，构建了开放词汇的载体关系场景图（CRSG），并在机器人导航过程中更新携带状态以反映场景的动态变化。基于CRSG，我们进一步提出了一种实例导航策略，将导航过程建模为马尔可夫决策过程。在每一步中，决策均由大型语言模型的常识知识和视觉-语言特征相似性提供信息。我们在Habitat模拟器中为日常常用物品设计了一系列长序列导航任务。结果表明，通过更新CRSG，机器人能高效导航至移动后的目标。此外，我们将算法部署在真实机器人上并验证了其实际有效性。
英文摘要：
In everyday life, frequently used objects like cups often have unfixed positions and multiple instances within the same category, and their carriers frequently change as well. As a result, it becomes challenging for a robot to efficiently navigate to a specific instance. To tackle this challenge, the robot must capture and update scene changes and plans continuously. However, current object navigation approaches primarily focus on semantic-level and lack the ability to dynamically update scene representation. This paper captures the relationships between frequently used objects and their static carriers. It constructs an open-vocabulary Carrier-Relationship Scene Graph (CRSG) and updates the carrying status during robot navigation to reflect the dynamic changes of the scene. Based on the CRSG, we further propose an instance navigation strategy that models the navigation process as a Markov Decision Process. At each step, decisions are informed by Large Language Model's commonsense knowledge and visual-language feature similarity. We designed a series of long-sequence navigation tasks for frequently used everyday items in the Habitat simulator. The results demonstrate that by updating the CRSG, the robot can efficiently navigate to moved targets. Additionally, we deployed our algorithm on a real robot and validated its practical effectiveness.
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。
