arXiv 2510.183162026-02-25cs.ROcs.AIcs.LG

MoMaGen: 为多步双臂移动操作生成演示数据以满足软约束和硬约束

MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation

Stanford University（斯坦福大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Amazon（亚马逊公司）

Chengshu Li, Mengdi Xu, Arpit Bahety, Hang Yin, Yunfan Jiang, Huang Huang, Josiah Wong, Sujay Garlanka, Cem Gokmen, Ruohan Zhang, Weiyu Liu, Jiajun Wu, Roberto … 展开作者

Chengshu Li, Mengdi Xu, Arpit Bahety, Hang Yin, Yunfan Jiang, Huang Huang, Josiah Wong, Sujay Garlanka, Cem Gokmen, Ruohan Zhang, Weiyu Liu, Jiajun Wu, Roberto Martín-Martín, Li Fei-Fei

备注：: Project website: momagen.github.io. The first four authors contribute equally. Accpeted to International Conference on Learning Representations (ICLR 2026)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

MoMaGen通过解决双臂移动操作中的可达性和可见性问题，生成多样化数据集以提升模仿学习策略的训练效果。

摘要：

从大规模、多样化的人类演示中学习模仿已显示在训练机器人方面是有效的，但收集此类数据是昂贵且耗时的。这种挑战在多步骤双臂移动操作中尤为突出，其中人类必须远程操作移动基座和两个高自由度的臂。先前的X-Gen工作已经开发了自动化数据生成框架用于静态（双臂）操作任务，通过增加少量人类演示在模拟中与新的场景配置来合成大规模数据集。然而，先前的工作在双臂移动操作任务中存在两大不足：1）移动基座引入了如何放置基座以使后续操作（可达性）的问题；2）主动相机引入了如何定位相机以生成视觉-运动策略的数据（可见性）的问题。为了解决这些挑战，MoMaGen将数据生成视为一个满足硬约束（例如可达性）的同时平衡软约束（例如导航中的可见性）的约束优化问题。这种形式能够推广到大多数现有的自动化数据生成方法，并为未来的方法提供原则性的基础。我们在四个多步骤双臂移动操作任务上进行了评估，并发现MoMaGen能够生成比先前方法更多的多样化数据集。由于数据集的多样性，我们还显示，由MoMaGen生成的数据可以使用单个来源演示来训练成功的模仿学习策略。此外，训练后的策略可以用非常少量的真实世界数据（40个演示）进行微调，以成功部署在真实的机器人硬件上。更多细节请参见我们的项目页面：momagen.github.io。

英文摘要：

Imitation learning from large-scale, diverse human demonstrations has been shown to be effective for training robots, but collecting such data is costly and time-consuming. This challenge intensifies for multi-step bimanual mobile manipulation, where humans must teleoperate both the mobile base and two high-DoF arms. Prior X-Gen works have developed automated data generation frameworks for static (bimanual) manipulation tasks, augmenting a few human demos in simulation with novel scene configurations to synthesize large-scale datasets. However, prior works fall short for bimanual mobile manipulation tasks for two major reasons: 1) a mobile base introduces the problem of how to place the robot base to enable downstream manipulation (reachability) and 2) an active camera introduces the problem of how to position the camera to generate data for a visuomotor policy (visibility). To address these challenges, MoMaGen formulates data generation as a constrained optimization problem that satisfies hard constraints (e.g., reachability) while balancing soft constraints (e.g., visibility while navigation). This formulation generalizes across most existing automated data generation approaches and offers a principled foundation for developing future methods. We evaluate on four multi-step bimanual mobile manipulation tasks and find that MoMaGen enables the generation of much more diverse datasets than previous methods. As a result of the dataset diversity, we also show that the data generated by MoMaGen can be used to train successful imitation learning policies using a single source demo. Furthermore, the trained policy can be fine-tuned with a very small amount of real-world data (40 demos) to be succesfully deployed on real robotic hardware. More details are on our project page: momagen.github.io.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。