VIRDO: Visio-tactile Implicit Representations of Deformable Objects
VIRDO: Visio-tactile Implicit Representations of Deformable Objects
复制标题
DOI：
10.1109/icra46639.2022.9812097
复制
发表时间：
2022-02
期刊：
影响因子：
--
通讯作者：
Youngsun Wi;Peter R. Florence;Andy Zeng;Nima Fazeli
中科院分区：
文献类型：
--
作者：
Youngsun Wi;Peter R. Florence;Andy Zeng;Nima Fazeli
可变形对象操作需要与机器人传感模式兼容的计算效率表示。在本文中，我们提出了VIRDO：一种隐式的、多模态的、连续的形变弹性物体表示。VIRDO直接对视觉（点云）和触觉（反作用力）模式进行操作，并学习接触位置和力的丰富潜在嵌入，以预测受外部接触影响的物体变形。在这里，我们展示了virdo的能力：i)产生具有密集无监督对应的高保真跨模态重建，ii)推广到看不见的接触形成，以及iii)使用部分视触觉反馈进行状态估计。https://github.com/MMintLab/VIRDO
Deformable object manipulation requires computationally efficient representations that are compatible with robotic sensing modalities. In this paper, we present VIRDO: an implicit, multi-modal, and continuous representation for deformable-elastic objects. VIRDO operates directly on visual (point cloud) and tactile (reaction forces) modalities and learns rich latent embeddings of contact locations and forces to predict object deformations subject to external contacts. Here, we demonstrate VIRDOs ability to: i) produce high-fidelity cross-modal reconstructions with dense unsupervised correspondences, ii) generalize to unseen contact formations, and iii) state-estimation with partial visio-tactile feedback. https://github.com/MMintLab/VIRDO