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 2606.26408cs.RO
收藏

探索扩散模型在约束逆运动学中的内在几何结构

Exploring the Intrinsic Geometry of Diffusion Models with Constrained Inverse Kinematics

Institute for Aerospace Studies, University of Toronto(航空航天研究所以及多伦多大学)

Miguel Angel Rogel Garcia, Phone Thiha Kyaw, Jonathan Kelly

AI总结:

通过约束逆运动学问题,研究扩散模型能否恢复数据流形的内在几何结构,实验表明模型得分函数恢复的内在维度与解析自由度匹配,且潜在空间线性插值保持约束流形结构。

摘要:

最近的研究表明,扩散模型可以恢复其训练数据流形中的几何结构,但迄今为止的支持证据主要来自自然图像数据,其底层几何结构本身是未知的。我们在一个几何结构可解析处理的设置中研究这个问题:约束逆运动学(IK)。每个任务空间约束定义一个具有已知内在维度的配置空间流形,为评估模型学习的几何结构提供了直接的真实数据。对于6自由度UR5和7自由度Franka,我们训练了一个单一的条件扩散模型,涵盖七个约束族,从离散IK分支到自运动流形。我们的实证结果表明,从模型得分函数恢复的内在维度与两个机器人上相应约束流形的解析自由度相匹配。此外,潜在空间中的线性插值导致生成的解保持接近适当的约束流形,表明学习到的表示进一步捕获了约束族的内在维度之外的几何结构。因此,约束逆运动学为研究扩散模型学习的内在几何结构提供了一个受控环境。

英文摘要:

Recent studies suggest that diffusion models can recover geometric structure in the data they are trained on, yet the supporting evidence has so far come mostly from natural-image data, where the underlying geometry itself is unknown. We study this question in a setting where the geometry is analytically tractable: constrained inverse kinematics (IK). Each task-space constraint defines a configuration-space manifold with known intrinsic dimension, giving direct ground truth for evaluating the geometry learned by the model. For each of the 6-DoF UR5 and 7-DoF Franka, we train a single conditional diffusion model across seven constraint families, spanning solution manifolds from discrete IK branches to self-motion manifolds. Our empirical results reveal that the intrinsic dimension recovered from the model's score function matches the analytical degrees of freedom of the corresponding constraint manifold across both robots. Moreover, linear interpolation in the latent space leads to generated solutions that remain close to the appropriate constraint manifold, indicating that the learned representation further captures geometric structure of the constraint family beyond intrinsic dimension alone. Constrained IK therefore offers a controlled setting for studying the intrinsic geometry learned by diffusion models.

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。

↑