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. Code, data and videos are avaible on https://unidoormanip.github.io/.

翻译：学习一种涵盖不同类别、几何结构和机制的通用门操控策略，对于未来具身智能体在复杂广阔的真实场景中有效工作至关重要。由于数据集有限且仿真环境不真实，以往的工作难以在各类门上均取得良好性能。本研究构建了一种新型的门操控环境，该环境能反映不同的真实门操控机制，并进一步为该环境配备了一个大规模门数据集，涵盖6大门类、数百种门体和门把手，形成数千种不同的门实例。此外，为更好地模拟真实场景，我们引入移动机器人作为智能体，并采用部分遮挡的点云作为观测信息——这些在以往工作中未被考虑，但对实际应用具有重要意义。为学习跨越多种门的通用策略，我们提出一种新颖框架，将整个操控过程解耦为三个阶段，并通过按推理的逆序训练进行整合。大量实验验证了设计的有效性，并展示了我们框架的强大性能。代码、数据和视频请访问https://unidoormanip.github.io/。