Generating Shape Transitions of Deformable Linear Objects Using Generative Adversarial Networks
Generating Shape Transitions of Deformable Linear Objects Using Generative Adversarial Networks
复制标题
DOI：
10.1109/icma54519.2022.9856119
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Kimitoshi Yamazaki;Ryo Matsuura;S. Arnold
中科院分区：
文献类型：
--
作者：
Kimitoshi Yamazaki;Ryo Matsuura;S. Arnold
本文提出了一个用于生成可变形线性物体形状转换的框架。我们采用基于gan的方法来生成物体变形，而不依赖于物理模拟。我们将可变形的线性对象表示为点链，并将单个形状配置表示为低维潜在空间中的点。我们提出了一种训练方法来获得这些潜在表征。然后，我们提出了一种生成和可视化光滑变形的方法。此外，我们还提出了一种方法来模拟当物体的一个端点在给定方向上移动时物体将如何变形。我们对生成端点线性位移的形状转换任务的方法进行了评估。
This paper presents a framework for generating shape transitions for deformable linear objects. We adopt a GAN-based approach to generate object deformations without reliance on physics simulation. We represent the deformable linear object as a point chain, and let individual shape configurations be represented as points in a low-dimensional latent space. We propose a training method for obtaining these latent representations. Then we propose a method for generating and visualizing smooth deformations. Furthermore, we propose a method for simulating how the object will deform when one of its terminal points would be moved in a given direction. We evaluate the method on the task of generating shape transitions for linear displacements of the terminal points.