arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.05412cs.RO
收藏

LaSeSOM:一个软对象操作的潜在语义表示框架

LaSeSOM: A Latent and Semantic Representation Framework for Soft Object Manipulation

The Hong Kong Polytechnic University(香港理工大学);Delft University of Technology(代尔夫特理工大学)

Peng Zhou, Jihong Zhu, Shengzeng Huo, David Navarro-Alarcon

摘要:

软物体操纵最近在机器人领域内受到欢迎,因为它在许多经济重要领域中具有潜在的应用。虽然最近在这些类型的任务中取得了很大的进展,但大多数最先进的方法都是针对特定情况的;它们只能用于执行单个变形任务(例如弯曲),因为它们的形状表示算法通常依赖于“硬编码”特征。在本文中,我们提出了LaSeSOM,一个新的反馈潜在表示框架的语义软对象操作。我们的新方法在低层几何特征提取和高层语义形状分析之间引入了内部潜在表示层;这允许识别每个压缩的语义函数并从不同的特征提取级别形成有效的形状分类器。所提出的潜在框架使软对象表示更加通用(独立于对象的几何形状和机械特性)和可扩展(它可以与1D/2D/3D任务一起工作)。它的高级语义层使执行(准)形状规划任务与软物体,一个有价值的和未充分利用的能力,在许多软操作任务。为了验证这种新的方法,我们报告了一个详细的实验研究与机器人机械手。

英文摘要:

Soft object manipulation has recently gained popularity within the robotics community due to its potential applications in many economically important areas. Although great progress has been recently achieved in these types of tasks, most state-of-the-art methods are case-specific; They can only be used to perform a single deformation task (e.g. bending), as their shape representation algorithms typically rely on "hard-coded" features. In this paper, we present LaSeSOM, a new feedback latent representation framework for semantic soft object manipulation. Our new method introduces internal latent representation layers between low-level geometric feature extraction and high-level semantic shape analysis; This allows the identification of each compressed semantic function and the formation of a valid shape classifier from different feature extraction levels. The proposed latent framework makes soft object representation more generic (independent from the object's geometry and its mechanical properties) and scalable (it can work with 1D/2D/3D tasks). Its high-level semantic layer enables to perform (quasi) shape planning tasks with soft objects, a valuable and underexplored capability in many soft manipulation tasks. To validate this new methodology, we report a detailed experimental study with robotic manipulators.

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。

↑