arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.13229cs.RO
收藏

通过结合可微滚动与几何约束的轨迹优化实现多指操作

Multi-finger Manipulation via Trajectory Optimization with Differentiable Rolling and Geometric Constraints

University of Michigan(密歇根大学);Honda Research Institute USA(美国本田研究所)

Fan Yang, Thomas Power, Sergio Aguilera Marinovic, Soshi Iba, Rana Soltani Zarrin, Dmitry Berenson

AI总结:

本文提出融合物体 SDF 与采样的可微接触、滚动约束轨迹优化方法,处理复杂几何下的多指灵巧操作,并在基准与真实任务中验证其优于基线且可跨越 sim2real 差距。

摘要:

以可微方式参数化手指滚动以及手指与物体之间的接触,对于将灵巧操作表述为轨迹优化问题十分重要。以往方法通常假设机器人和物体具有简化几何形状,或者没有显式建模手指滚动;与之不同,我们提出一种方法,通过同时考虑机器人和物体的非平凡几何形状,进一步扩展灵巧操作的能力。通过将物体的 Signed Distance Field(SDF,有符号距离场)与一种采样方法相结合,我们的方法以可微方式估计接触及与滚动相关的变量,并将这些变量纳入轨迹优化框架。该表述自然允许手指滚动行为涌现,使机器人能够局部调整接触点。为评估我们的方法,我们引入了一个基准,其中包含具有挑战性的多指灵巧操作任务,例如转动螺丝刀和手内重新定向。在达到期望物体构型以及避免物体掉落方面,我们的方法优于基线方法。我们还将该方法成功应用于真实世界中的螺丝刀转动任务和长方体对齐任务,证明了其对 sim2real 差距的鲁棒性。

英文摘要:

Parameterizing finger rolling and finger-object contacts in a differentiable manner is important for formulating dexterous manipulation as a trajectory optimization problem. In contrast to previous methods which often assume simplified geometries of the robot and object or do not explicitly model finger rolling, we propose a method to further extend the capabilities of dexterous manipulation by accounting for non-trivial geometries of both the robot and the object. By integrating the object's Signed Distance Field (SDF) with a sampling method, our method estimates contact and rolling-related variables in a differentiable manner and includes those in a trajectory optimization framework. This formulation naturally allows for the emergence of finger-rolling behaviors, enabling the robot to locally adjust the contact points. To evaluate our method, we introduce a benchmark featuring challenging multi-finger dexterous manipulation tasks, such as screwdriver turning and in-hand reorientation. Our method outperforms baselines in terms of achieving desired object configurations and avoiding dropping the object. We also successfully apply our method to a real-world screwdriver turning task and a cuboid alignment task, demonstrating its robustness to the sim2real gap.

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。

↑