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 2104.09194cs.RO
收藏

基于可微力闭合估计的任意手结构的多样性和物理稳定抓取

Synthesizing Diverse and Physically Stable Grasps with Arbitrary Hand Structures using Differentiable Force Closure Estimator

Beijing Institute for General Artificial Intelligence (BIGAI)(北京通用人工智能研究院);Peking University(北京大学);Tsinghua University(清华大学)

Tengyu Liu, Zeyu Liu, Ziyuan Jiao, Yixin Zhu, Song-Chun Zhu

摘要:

现有的抓取合成方法是分析或数据驱动的。前者往往局限于特定的应用范围。后者严重依赖于演示,因此存在泛化问题;例如,用人类抓取数据训练的模型将难以转移到3指抓取器。为了解决这些缺陷,我们制定了一个快速和可微力闭合估计方法,能够产生不同的和物理稳定的把握任意手结构,没有任何训练数据。虽然力闭合通常作为把握质量的衡量标准,但由于其高计算复杂性,它尚未被广泛采用作为把握合成的优化目标;相比之下,所提出的可微方法可以在毫秒内测试力闭合。在实验中,我们验证了所提出的方法的有效性,在6个不同的设置。

英文摘要:

Existing grasp synthesis methods are either analytical or data-driven. The former one is oftentimes limited to specific application scope. The latter one depends heavily on demonstrations, thus suffers from generalization issues; e.g., models trained with human grasp data would be difficult to transfer to 3-finger grippers. To tackle these deficiencies, we formulate a fast and differentiable force closure estimation method, capable of producing diverse and physically stable grasps with arbitrary hand structures, without any training data. Although force closure has commonly served as a measure of grasp quality, it has not been widely adopted as an optimization objective for grasp synthesis primarily due to its high computational complexity; in comparison, the proposed differentiable method can test a force closure within milliseconds. In experiments, we validate the proposed method's efficacy in 6 different settings.

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。

↑