Learning a universal manipulation policy encompassing doors with diverse categories, geometries and mechanisms, is crucial for future embodied agents to effectively work in complex and broad real-world scenarios. Due to the limited datasets and unrealistic simulation environments, previous works fail to achieve good performance across various doors. In this work, we build a novel door manipulation environment reflecting different realistic door manipulation mechanisms, and further equip this environment with a large-scale door dataset covering 6 door categories with hundreds of door bodies and handles, making up thousands of different door instances. Additionally, to better emulate real-world scenarios, we introduce a mobile robot as the agent and use the partial and occluded point cloud as the observation, which are not considered in previous works while possessing significance for real-world implementations. To learn a universal policy over diverse doors, we propose a novel framework disentangling the whole manipulation process into three stages, and integrating them by training in the reversed order of inference. Extensive experiments validate the effectiveness of our designs and demonstrate our framework's strong performance.

翻译：学习涵盖不同类别、几何形状和机制的门通用操控策略，对于未来具身代理在复杂且广泛的真实场景中高效工作至关重要。由于数据集有限且仿真环境不真实，以往的工作无法在多种门上取得良好性能。在这项工作中，我们构建了一个新颖的门操控环境，能够反映不同的真实门操控机制，并进一步为这一环境配备了一个大规模门数据集，涵盖6个门类别，包含数百种门体和门把手，形成了数千种不同的门实例。此外，为了更好地模拟真实场景，我们引入移动机器人作为代理，并使用部分遮挡的点云作为观测，这些在以往的工作中未被考虑，但对实际应用具有重要意义。为了学习跨多种门的通用策略，我们提出了一个新颖的框架，将整个操控过程分解为三个阶段，并通过按推理逆序进行训练来整合它们。大量实验验证了我们设计的有效性，并展示了框架的强大性能。