Bimanual manipulation is imperative yet challenging for robots to execute complex tasks, requiring coordinated collaboration between two arms. However, existing methods for bimanual manipulation often rely on costly data collection and training, struggling to generalize to unseen objects in novel categories efficiently. In this paper, we present Bi-Adapt, a novel framework designed for efficient generalization for bimanual manipulation via semantic correspondence. Bi-Adapt achieves cross-category affordance mapping by leveraging the strong capability of vision foundation models. Fine-tuning with restricted data on novel categories, Bi-Adapt exhibits notable generalization to out-of-category objects in a zero-shot manner. Extensive experiments conducted in both simulation and real-world environments validate the effectiveness of our approach and demonstrate its high efficiency, achieving a high success rate on different benchmark tasks across novel categories with limited data. Project website: https://biadapt-project.github.io/

翻译：双手操作对于机器人执行复杂任务至关重要，但也极具挑战性，它需要两只手臂之间的协调协作。然而，现有的双手操作方法通常依赖于昂贵的数据收集和训练，难以高效地泛化到新类别中的未见物体。本文提出Bi-Adapt，这是一个通过语义对应实现高效双手操作泛化的新颖框架。Bi-Adapt通过利用视觉基础模型的强大能力，实现了跨类别的可供性映射。通过对新类别进行有限数据的微调，Bi-Adapt以零样本方式展现出对类别外物体的显著泛化能力。在仿真和真实环境中进行的大量实验验证了我们方法的有效性，并证明了其高效率，能够在有限数据下，在不同新类别的基准任务上实现高成功率。项目网站：https://biadapt-project.github.io/