RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
打开互动全文版（逐段中英对照 + 图/公式 + 论文问答）→双臂操作在机器人领域至关重要，但由于协调两个机械臂的固有复杂性（导致多模态动作分布）以及训练数据的稀缺，开发基础模型极具挑战性。本文提出了机器人扩散变换器（RDT），这是一种开创性的双臂操作扩散基础模型。RDT 基于扩散模型有效表示多模态性，通过可扩展变换器的创新设计处理多模态输入的异质性，并捕捉机器人数据的非线性和高频特性。为解决数据稀缺问题，我们进一步引入了物理可解释的统一动作空间，该空间能够统一各种机器人的动作表示，同时保留原始动作的物理意义，促进可迁移物理知识的学习。凭借这些设计，我们成功在迄今为止最大的多机器人数据集上预训练了 RDT，并将其扩展至 12 亿参数，这是目前最大的基于扩散的机器人操作基础模型。最后，我们在自创的包含 6000 多个片段的多任务双臂数据集上对 RDT 进行微调，以完善其操作能力。真实机器人实验表明，RDT 显著优于现有方法。它能够零样本泛化到未见过的物体和场景，理解并遵循语言指令，仅需 1~5 次演示即可学习新技能，并有效处理复杂灵巧的任务。代码和视频请参见 https://rdt-robotics.github.io/rdt-robotics/。
Bimanual manipulation is essential in robotics, yet developing foundation models is extremely challenging due to the inherent complexity of coordinating two robot arms (leading to multi-modal action distributions) and the scarcity of training data. In this paper, we present the Robotics Diffusion Transformer (RDT), a pioneering diffusion foundation model for bimanual manipulation. RDT builds on diffusion models to effectively represent multi-modality, with innovative designs of a scalable Transformer to deal with the heterogeneity of multi-modal inputs and to capture the nonlinearity and high frequency of robotic data. To address data scarcity, we further introduce a Physically Interpretable Unified Action Space, which can unify the action representations of various robots while preserving the physical meanings of original actions, facilitating learning transferrable physical knowledge. With these designs, we managed to pre-train RDT on the largest collection of multi-robot datasets to date and scaled it up to 1.2B parameters, which is the largest diffusion-based foundation model for robotic manipulation. We finally fine-tuned RDT on a self-created multi-task bimanual dataset with over 6K+ episodes to refine its manipulation capabilities. Experiments on real robots demonstrate that RDT significantly outperforms existing methods. It exhibits zero-shot generalization to unseen objects and scenes, understands and follows language instructions, learns new skills with just 1~5 demonstrations, and effectively handles complex, dexterous tasks. We refer to https://rdt-robotics.github.io/rdt-robotics/ for the code and videos.