Recent work in the construction of 3D scene graphs has enabled mobile robots to build large-scale hybrid metric-semantic hierarchical representations of the world. These detailed models contain information that is useful for planning, however how to derive a planning domain from a 3D scene graph that enables efficient computation of executable plans is an open question. In this work, we present a novel approach for defining and solving Task and Motion Planning problems in large-scale environments using hierarchical 3D scene graphs. We identify a method for building sparse problem domains which enable scaling to large scenes, and propose a technique for incrementally adding objects to that domain during planning time to avoid wasting computation on irrelevant elements of the scene graph. We test our approach in two hand crafted domains as well as two scene graphs built from perception, including one constructed from the KITTI dataset. A video supplement is available at https://youtu.be/63xuCCaN0I4.

翻译：近期在三维场景图构建方面的研究使移动机器人能够构建大规模混合度量-语义层级化的世界表示。这些精细模型包含对规划有用的信息，但如何从三维场景图推导出能高效计算可执行规划的规划域仍是一个开放问题。本文提出一种创新方法，利用分层三维场景图在大规模环境中定义并解决任务与运动规划问题。我们确定了一种构建稀疏问题域的方法，使其能够扩展至大规模场景，并提出了在规划期间向该域增量添加对象的技术，从而避免对场景图中无关元素的无效计算。我们在两个手工构建的域以及两个基于感知构建的场景图（包括一个从KITTI数据集构建的场景图）上测试了该方法。视频补充材料见https://youtu.be/63xuCCaN0I4。