基于李群约束MeanFlow的快速生成式抓取

中文摘要 AI 辅助

抓取合成是机器人操作的核心任务，其解通常形成多模态分布而非点估计。生成式机器人抓取旨在通过深度生成模型（如扩散模型和基于流的方法）学习该分布。这类生成模型的迭代特性使其具有灵活性和泛化性，但多步采样会阻碍机器人所需的时间关键型操作。我们提出一种基于李群$\boldsymbol{\text{MeanFlow}}$的快速生成式抓取方法，该方法在乘积李群$\boldsymbol{\text{G}} = \boldsymbol{\text{SO}}(3) \times \boldsymbol{\text{R}}^3$上构建，训练目标将纯代数半群一致性条件与$\boldsymbol{\text{G}}$上的黎曼条件流匹配相结合，使平均速度锚定到数据分布。所得到的李群约束MeanFlow公式可在$\boldsymbol{\text{≤5}}$次网络评估中采样出可靠抓取，在ACRONYM数据集上达到与最先进扩散模型和基于流的模型相当的抓取生成性能，推理延迟为毫秒级，加速比最高达$\boldsymbol{39\times}$。我们进一步证明，该方法无需额外训练或领域适配即可直接迁移到真实世界机器人抓取，在观测噪声下表现出鲁棒的抓取合成能力。

英文摘要

Grasp synthesis is a core task in robotic manipulation, for which the solution typically forms a multimodal distribution rather than a point estimate. Generative robotic grasping aims to learn this distribution with deep generative models such as diffusion and flow-based approaches. The iterative nature of such generative models makes them flexible and generalizable; however, multi-step sampling impedes the time-critical operation required in robotics. We devise an approach to fast generative grasping based on MeanFlow on the product Lie group $\mathcal{G} = \mathrm{SO}(3) \times \mathbb{R}^3$. The training objective couples a purely algebraic semigroup consistency condition with Riemannian Conditional Flow Matching on $\mathcal{G}$ that anchors the average velocity to the data distribution. The resulting Lie Group-constrained MeanFlow formulation samples reliable grasps in $\leq 5$ network evaluations, matching the grasp generation performance of state-of-the-art diffusion and flow-based models on the ACRONYM dataset at millisecond-scale inference latency (up to $39\times$ speed-up). We further demonstrate that the approach directly translates to real-world robotic grasping without additional training or domain adaptation, exhibiting robust grasp synthesis under observation noise.

发表机构

• Purdue University（普渡大学）

机构由 AI 辅助整理，请以论文原文为准。