arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.14833cs.RO
收藏

将潜在运动适应扩展到协调的双臂操作

Scaling Latent Motor Adaptation to Coordinated Bimanual Manipulation

University of Oxford(牛津大学);Oxford Robotics Institute(牛津机器人研究所);Technical University of Munich(慕尼黑工业大学);Toyota Motor Europe(丰田汽车欧洲公司)

Seung-Bin Joo, Alessandro Albini, Luca Wiehe, Perla Maiolino, Daniel Olmeda Reino, João F. Henriques

AI总结:

本研究验证了快速运动适应(RMA)范式可扩展至双臂操作,其在双臂拾取提升任务上表现优于PPO策略,且能实现仿真到真实的直接迁移,为鲁棒控制扩展提供了结构支持。

摘要:

在不确定的物体动力学和几何条件下实现鲁棒操作仍是现实机器人技术的核心挑战。基于固定假设训练的策略,当物体质量、摩擦系数、尺寸或形状发生变化时,性能会下降。基于嵌入的适应方法,如快速运动适应(Rapid Motor Adaptation, RMA),通过将动作条件化于从交互历史推断出的环境动力学潜在表示来解决这一问题。本研究探究该范式是否能从单臂设置扩展到协调的双臂操作,其中更高维度的控制、耦合接触以及共享物体力引入了额外复杂性。我们在三个接触丰富的ManiSkill任务上评估双臂RMA,这些任务采用随机YCB物体属性。双臂RMA利用观测-动作历史和双腕深度图像,在双臂拾取和提升任务上保持特权策略性能,而未进行潜在条件化的匹配固定PPO策略成功率较低;所有方法在长 horizon 堆叠任务上仍存在局限。我们进一步在双Franka提升任务上展示了无需真实世界微调的直接仿真到真实迁移。这些结果共同表明,潜在条件化为将鲁棒控制扩展到协调双臂系统提供了有用结构,而长 horizon 任务需要额外的时间结构。

英文摘要:

Robust manipulation under uncertain object dynamics and geometry remains a core challenge in real-world robotics. Policies trained under fixed assumptions often degrade when object mass, friction, scale, or shape vary. Embedding-based adaptation methods such as Rapid Motor Adaptation (RMA) address this by conditioning actions on latent representations of environment dynamics inferred from interaction history. We investigate whether this paradigm scales from single arm settings to coordinated bimanual manipulation, where higher dimensional control, coupled contacts, and shared object forces introduce additional complexity. We evaluate bimanual RMA on three contact-rich ManiSkill tasks with randomized YCB object properties. Bimanual RMA, using observation-action history and dual wrist depth images, retains privileged policy performance on bimanual picking and lifting, while an otherwise matched stationary PPO policy without latent conditioning achieves low success; all methods remain limited on long-horizon stacking. We further demonstrate direct sim-to-real transfer on a dual Franka lifting task without real-world finetuning. Together, these results suggest that latent conditioning provides useful structure for scaling robust control to coordinated bimanual systems, while longer horizon tasks require additional temporal structure.

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。

↑