Language is compositional; an instruction can express multiple relation constraints to hold among objects in a scene that a robot is tasked to rearrange. Our focus in this work is an instructable scene-rearranging framework that generalizes to longer instructions and to spatial concept compositions never seen at training time. We propose to represent language-instructed spatial concepts with energy functions over relative object arrangements. A language parser maps instructions to corresponding energy functions and an open-vocabulary visual-language model grounds their arguments to relevant objects in the scene. We generate goal scene configurations by gradient descent on the sum of energy functions, one per language predicate in the instruction. Local vision-based policies then re-locate objects to the inferred goal locations. We test our model on established instruction-guided manipulation benchmarks, as well as benchmarks of compositional instructions we introduce. We show our model can execute highly compositional instructions zero-shot in simulation and in the real world. It outperforms language-to-action reactive policies and Large Language Model planners by a large margin, especially for long instructions that involve compositions of multiple spatial concepts. Simulation and real-world robot execution videos, as well as our code and datasets are publicly available on our website: https://ebmplanner.github.io.

翻译：语言具有组合性；一条指令可以表达场景中物体之间需满足的多个关系约束，而机器人需要重新排列这些物体。本文聚焦于一种可指令驱动的场景重排框架，该框架能泛化至更长的指令以及训练时从未见过的空间概念组合。我们提出用相对物体排列的能量函数来表示语言指令所蕴含的空间概念。语言解析器将指令映射为对应的能量函数，而开放词汇的视觉-语言模型则将其参数与场景中的相关物体进行对应。我们通过对指令中每个语言谓词对应的能量函数之和进行梯度下降，来生成目标场景配置。随后，基于局部视觉的策略将物体重新定位到推断出的目标位置。我们在已有的指令引导操作基准测试以及我们引入的组合指令基准测试上评估了该模型。结果表明，我们的模型能够在仿真和真实世界中零样本地执行高度组合的指令。与语言到动作的反应式策略及大型语言模型规划器相比，我们的模型显著更优，尤其对于涉及多个空间概念组合的长指令。仿真和真实世界机器人执行视频，以及我们的代码和数据集，已公开在网站：https://ebmplanner.github.io。