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 2606.18092cs.ROcs.AI
收藏

EAGG: 通过几何感知图条件实现具身对齐的抓取生成

EAGG: Embodiment-Aligned Grasp Generation via Geometry-Aware Graph Conditioning

Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系);Beijing Moce Future Technology Co., Ltd.(北京墨策未来科技有限公司)

Wanhao Niu, Qiyan Ke, Yuan Sun, Hao Sun, Jie Xu, Muyuan Ma, Ruiqi Hu, Fuchun Sun

AI总结:

提出EAGG,一种通过拓扑感知末端执行器图和几何感知令牌实现跨末端执行器抓取生成的统一模型,在MultiGripperGrasp基准上达到56.17%平均成功率,并显著降低接触距离。

摘要:

跨末端执行器抓取生成旨在寻求一个统一的模型,能够泛化到不同物体以及从平行夹爪到灵巧末端执行器的不同具身形态。现有的抓取生成器通常针对固定具身设计,或使用静态描述符编码具身身份,当拓扑结构、驱动耦合和接触几何差异较大时,这会削弱迁移能力。我们提出EAGG,一种具身对齐的抓取生成器,通过拓扑感知的末端执行器图和具身特定的低维末端执行器控制空间来表示每个具身。一个冻结的末端执行器认知骨干将当前关节状态转换为几何感知令牌,作为可复用的形态先验,并通过迭代几何注入在采样过程中刷新这些令牌,使条件与不断演变的末端执行器几何保持同步。在MultiGripperGrasp基准上,EAGG在六个训练末端执行器上达到56.17%的平均成功率,与专门训练的差距在1.10个百分点以内,同时保持对微调和零样本末端执行器的迁移能力。迭代几何注入进一步将合并中位接触距离从0.239厘米降低到0.189厘米。这些结果表明,通过在共享生成器内对齐具身结构而非抑制具身差异,可以增强跨末端执行器抓取生成。代码可在该网址获取:https://this URL。

英文摘要:

Cross-end-effector grasp generation seeks a unified model that generalizes across objects and across embodiments ranging from parallel grippers to dexterous end effectors. Existing grasp generators are typically designed for a fixed embodiment or encode embodiment identity with a static descriptor, which weakens transfer when topology, actuation coupling, and contact geometry differ substantially. We present EAGG, an embodiment-aligned grasp generator that represents each embodiment with a topology-aware end-effector graph and an embodiment-specific low-dimensional end-effector control space. A frozen end-effector-cognition backbone converts the current articulated state into geometry-aware tokens that act as a reusable morphology prior, and iterative geometry injection refreshes these tokens throughout sampling so that conditioning remains synchronized with the evolving end-effector geometry. On the MultiGripperGrasp benchmark, EAGG reaches 56.17% average success across six training end effectors, remaining within 1.10 percentage points of specialized training while preserving transfer to finetuning and zero-shot end effectors. Iterative geometry injection further reduces the pooled median contact distance from 0.239 cm to 0.189 cm. These results show that cross-end-effector grasp generation is strengthened by aligning embodiment structure inside a shared generator rather than suppressing embodiment differences. Code is available at https://github.com/wanhaoniu/EAGG.

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。

↑